© 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. 26516
    Prev
    Next
    INDEX
    Explanations

    structured configuration files

    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
    킁
    -1.59
     célè
    -1.59
    ほとん
    -1.57
     miniaturka
    -1.55
    honestly
    -1.53
    unfortunately
    -1.53
    primarily
    -1.51
     fournit
    -1.48
     Preferencias
    -1.48
     yyb
    -1.45
    POSITIVE LOGITS
     as
    1.60
    ;
    1.59
     or
    1.56
     d
    1.47
     after
    1.46
     with
    1.43
     all
    1.41
     to
    1.41
     use
    1.38
     and
    1.37
    Activations Density 0.015%

    No Known Activations