© 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. 10-GEMMASCOPE-RES-131K
    4. 45074
    Prev
    Next
    INDEX
    Explanations

    difference than

    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_10/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
     at
    -2.69
     And
    -2.11
     Sadly
    -1.96
     Perhaps
    -1.94
     first
    -1.93
     Since
    -1.90
     AND
    -1.84
     or
    -1.81
     and
    -1.80
     Though
    -1.79
    POSITIVE LOGITS
    ྄
    2.17
     ‚
    2.11
    ⎔
    2.05
    乄
    2.02
     we
    1.96
     vinte
    1.81
    奩
    1.76
    GERS
    1.74
    ཊ
    1.73
     inny
    1.70
    Activations Density 0.005%

    No Known Activations