© 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-65K
    7. 587
    Prev
    Next
    INDEX
    Explanations

    '

    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_65k_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
    lbrakk
    2.40
    ----+---->
    2.39
    <unused1182>
    2.38
    <unused866>
    2.38
    <unused816>
    2.38
     gstlal
    2.38
     CCOc
    2.38
    imcoords
    2.37
     nCharString
    2.37
    FURNIZOR
    2.35
    POSITIVE LOGITS
    s
    1.54
    ↵
    1.02
    the
    0.97
    nya
    0.95
    os
    0.91
    of
    0.89
    ism
    0.88
    ↵↵
    0.86
    er
    0.85
    ist
    0.85
    Activations Density 1.030%

    No Known Activations