© 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. 527
    Prev
    Next
    INDEX
    Explanations

    ability and ease

    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
    azol
    2.29
    ochemical
    2.23
    ifying
    2.14
    ェ
    2.09
    ョ
    2.06
    apaccay
    2.05
     Nathan
    2.00
     листь
    1.97
    ografi
    1.96
    iros
    1.96
    POSITIVE LOGITS
     discriminate
    2.08
    easily
    2.04
    tobs
    1.99
     mắn
    1.96
     be
    1.89
    berra
    1.88
     easily
    1.87
     differentiate
    1.86
    겹
    1.85
    VICES
    1.82
    Activations Density 3.281%

    No Known Activations