© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66140
    Prev
    Next
    INDEX
    Explanations

    given names followed by surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ふと
    -1.60
    久しぶりに
    -1.53
    during
    -1.53
    久し
    -1.52
    already
    -1.50
    gives
    -1.43
    凄い
    -1.43
    為に
    -1.41
    凄く
    -1.40
     rassemb
    -1.38
    POSITIVE LOGITS
     of
    1.96
     from
    1.69
     by
    1.53
     if
    1.49
     in
    1.48
     with
    1.41
     without
    1.32
     after
    1.26
     at
    1.26
     (
    1.26
    Activations Density 0.030%

    No Known Activations