© 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. 76141
    Prev
    Next
    INDEX
    Explanations

    numbers and words

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

    language identification and conditionals

    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
    Not in Any Lists

    No Comments

    Negative Logits
    in
    0.59
    e
    0.50
    u
    0.47
    price
    0.46
    oretically
    0.46
    er
    0.46
    re
    0.46
    ed
    0.46
    rated
    0.46
    i
    0.46
    POSITIVE LOGITS
     Auswirkungen
    0.55
     பரு
    0.53
     onları
    0.53
     Cenomanian
    0.52
     zusätzlichen
    0.52
     ഗവേഷ
    0.51
     Pérez
    0.51
    Methylsulfanyl
    0.50
     நேரத்தில்
    0.49
     Lernen
    0.49
    Activations Density 0.002%

    No Known Activations