© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 207826
    Prev
    Next
    INDEX
    Explanations

    contact or inquiry

    np_acts-logits-general · gemini-2.5-flash-lite

    comments suggesting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ပေ
    0.52
     آسی
    0.50
     दशा
    0.48
    ötzlich
    0.46
     đặc
    0.46
     অবশ্যই
    0.45
    雓
    0.44
    ﯼ
    0.43
    ဆုံး
    0.43
     incumb
    0.43
    POSITIVE LOGITS
    ุก
    0.50
    ੱਚ
    0.43
     rebellion
    0.42
    Просе
    0.41
    CLE
    0.41
     SOCIAL
    0.41
    স্টি
    0.41
    RefIn
    0.40
     Process
    0.40
     Werke
    0.39
    Activations Density 0.000%

    No Known Activations