© 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. 151
    Prev
    Next
    INDEX
    Explanations

    vicuna model

    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
    宠物
    1.07
    Descripcion
    1.04
    জ্জনক
    1.03
    Dtls
    1.01
     onLoad
    0.98
    <unused2169>
    0.97
    <unused2197>
    0.95
    LastName
    0.95
     BSData
    0.94
    مول
    0.94
    POSITIVE LOGITS
    '
    0.87
    ®
    0.87
    ™
    0.86
    ’
    0.84
     came
    0.79
    .
    0.77
     Te
    0.73
     celebrated
    0.71
    ist
    0.71
     Ag
    0.70
    Activations Density 6.121%

    No Known Activations