© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 982
    Prev
    Next
    INDEX
    Explanations

    pecans or INT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    composed
    1.17
    ccco
    1.15
    COOH
    1.13
    betriebnahme
    1.12
    CCCO
    1.11
    KO
    1.08
    𝜁
    1.07
    ㅍ
    1.07
    resized
    1.07
    painter
    1.06
    POSITIVE LOGITS
     or
    1.70
    或
    1.48
     или
    1.47
    或者
    1.43
     أو
    1.43
     atau
    1.40
     ou
    1.35
     oder
    1.31
     或者
    1.29
    或是
    1.29
    Activations Density 2.053%

    No Known Activations