© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 2333
    Prev
    Next
    INDEX
    Explanations

    explanatory phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases related to branding and corporate presentation and client experience.

    oai_token-act-pair · gpt-5-nanoTriggered by @igorkuztech

    make

    np_max-act · gpt-5-miniTriggered by @igorkuztech

    the neuron responds strongly to very common, high-probability tokens (frequent function words and common verbs).

    oai_token-act-pair · gpt-5-miniTriggered by @igorkuztech

    uses of the verb “make” (including its inflected forms and common collocations).

    oai_token-act-pair · gpt-5Triggered by @igorkuztech
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    %@",
    1.57
    ==============]
    1.56
    ակ
    1.52
    igger
    1.51
    IZER
    1.49
    henius
    1.45
    istik
    1.43
    izer
    1.42
    ের
    1.42
    nau
    1.42
    POSITIVE LOGITS
    𝘭
    2.25
    INTRESOURCE
    2.17
     headway
    2.10
    ள
    2.03
    
    1.87
    elabel
    1.87
    leine
    1.86
    𝙇
    1.83
     unqualified
    1.81
     sure
    1.79
    Activations Density 0.471%

    No Known Activations