© 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. 4018
    Prev
    Next
    INDEX
    Explanations

    Instagram, Facebook, X

    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
    斎
    0.44
    ྭ
    0.43
     なり
    0.42
    ْن
    0.42
     በሽታ
    0.42
    变换
    0.41
    🜨
    0.40
     abuse
    0.40
    សម្រ
    0.40
     ሂደ
    0.40
    POSITIVE LOGITS
     الاعداد
    0.42
     vela
    0.42
     Гон
    0.42
    ecu
    0.41
     जिन्हें
    0.41
    eln
    0.40
     JY
    0.40
     Ing
    0.40
     Toolkit
    0.40
    0.39
    Activations Density 0.017%

    No Known Activations