© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67337
    Prev
    Next
    INDEX
    Explanations

    BUT followed by contrast or new information

    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
     joys
    -1.34
     verdure
    -1.30
    ÑOS
    -1.29
     många
    -1.22
    issional
    -1.22
    cinations
    -1.21
     Sosial
    -1.20
     kudos
    -1.19
     rivets
    -1.19
     bander
    -1.19
    POSITIVE LOGITS
     that
    1.88
    nargs
    1.63
     be
    1.54
    </strong>
    1.52
    ჻
    1.41
    mappedBy
    1.40
     informacje
    1.38
     right
    1.36
     durant
    1.36
    ,
    1.34
    Activations Density 0.024%

    No Known Activations