© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108514
    Prev
    Next
    INDEX
    Explanations

    zero-shot or few-shot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     funders
    0.43
    4
    0.42
     analyse
    0.41
    Sl
    0.41
     fir
    0.41
     macromolecules
    0.41
     sorular
    0.41
     extras
    0.40
     ordine
    0.40
    /*
    0.39
    POSITIVE LOGITS
     思う
    0.52
     һәм
    0.48
     və
    0.47
    ியின்
    0.45
    通风
    0.45
    🔇
    0.43
    AssetDiscovery
    0.43
     ምክንያት
    0.43
    谧
    0.42
     ਇੱਕ
    0.42
    Activations Density 0.003%

    No Known Activations