© 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-65K
    7. 64545
    Prev
    Next
    INDEX
    Explanations

    scope and activities

    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_65k_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
    น
    0.46
     West
    0.45
    ו
    0.44
    }^{
    0.44
     fore
    0.42
    ת
    0.41
    ಕೂ
    0.40
    و
    0.39
    ត
    0.39
     genuinely
    0.38
    POSITIVE LOGITS
    elun
    0.50
    िस
    0.47
    athar
    0.47
    unica
    0.46
    icolo
    0.46
    リー
    0.46
    ॉन
    0.46
    )$;
    0.46
    ahit
    0.46
    hasilan
    0.46
    Activations Density 0.002%

    No Known Activations