© 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. 17-GEMMASCOPE-2-RES-16K
    7. 2055
    Prev
    Next
    INDEX
    Explanations

    word counts and lengths

    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_17_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
     Horace
    0.89
    icast
    0.89
    Betty
    0.79
     Girl
    0.79
     nrows
    0.78
    少量
    0.77
     男の子
    0.77
    큘
    0.76
     Miniature
    0.76
    若干
    0.76
    POSITIVE LOGITS
     higher
    0.97
     acima
    0.96
     deviations
    0.92
    higher
    0.91
    above
    0.86
     perfecto
    0.86
     prossimo
    0.81
    较高
    0.81
    lomer
    0.79
     above
    0.78
    Activations Density 0.318%

    No Known Activations