© 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. 171959
    Prev
    Next
    INDEX
    Explanations

    writer developing ideas

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

    lack of

    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
     ();
    0.48
     Boo
    0.48
     पीड़ितों
    0.47
     korban
    0.46
     Wife
    0.46
     kapan
    0.46
     vítimas
    0.45
    </i>
    0.44
    boru
    0.44
     Privy
    0.43
    POSITIVE LOGITS
     excluded
    0.49
     ቀለም
    0.48
     ሽፋን
    0.47
     exclude
    0.47
    érieure
    0.47
    Từ
    0.46
    邇
    0.46
    ORTH
    0.44
    ーション
    0.44
    aternion
    0.44
    Activations Density 0.003%

    No Known Activations