© 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. 1133
    Prev
    Next
    INDEX
    Explanations

    Key takeaways communicating like a line

    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
    𒀖
    1.83
    BEDATUM
    1.80
     Pusenk
    1.79
    FcmError
    1.79
    𒁇
    1.79
    STARGO
    1.78
    𒌵
    1.77
    𒈲
    1.77
    𒂟
    1.77
     मेरिये
    1.77
    POSITIVE LOGITS
    .
    1.89
     to
    1.83
     a
    1.77
     in
    1.56
     by
    1.55
     is
    1.47
     of
    1.45
    :
    1.43
     for
    1.41
    ,
    1.38
    Activations Density 0.355%

    No Known Activations