© 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. 27524
    Prev
    Next
    INDEX
    Explanations

    windward side

    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
     подготов
    0.45
    ጀት
    0.45
    тивного
    0.44
    煜
    0.43
     financiar
    0.42
    畱
    0.42
    她们
    0.42
     Robins
    0.42
    <unused325>
    0.42
    থন
    0.42
    POSITIVE LOGITS
    v
    0.61
    ik
    0.54
    vor
    0.50
    im
    0.49
    il
    0.48
    ot
    0.48
     খুবই
    0.48
    os
    0.48
    ic
    0.46
     পাথ
    0.46
    Activations Density 0.042%

    No Known Activations