© 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. 8974
    Prev
    Next
    INDEX
    Explanations

    types of licenses

    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
     ট্যাব
    1.23
    ContextProvider
    1.22
    槽
    1.17
     diálogo
    1.16
     অবহিত
    1.15
     editable
    1.15
    ㈣
    1.15
     பிரதமர்
    1.15
     Сегодня
    1.14
     மில்லியன்
    1.14
    POSITIVE LOGITS
     manifolds
    1.10
    sonsten
    1.01
     Korn
    0.94
    леко
    0.93
     Bow
    0.92
    0.91
     manifold
    0.91
     karn
    0.90
     Porta
    0.89
    킷
    0.89
    Activations Density 0.001%

    No Known Activations