© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14435
    Prev
    Next
    INDEX
    Explanations

    turbulent

    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_7_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
    гла
    2.48
    𝒍
    2.48
    inin
    2.24
    ей
    2.24
     velho
    2.23
    othelium
    2.17
     pouce
    2.16
    unlink
    2.16
     disclosing
    2.14
     diploid
    2.14
    POSITIVE LOGITS
    ✠
    2.25
    ಿಂದ
    2.21
     tok
    2.17
     earners
    2.09
    LayoutParams
    2.08
    ῆ
    2.06
    न्होंने
    2.05
     되었
    2.04
     incoming
    2.03
     ἀ
    2.01
    Activations Density 0.020%

    No Known Activations