© 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. 67965
    Prev
    Next
    INDEX
    Explanations

    See related research

    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
    1
    -1.90
    های
    -1.88
    —
    -1.59
    ="
    -1.58
    othes
    -1.55
    ,‎
    -1.53
    \|^{
    -1.48
    4
    -1.48
     impec
    -1.48
    乓
    -1.48
    POSITIVE LOGITS
     This
    1.79
     you
    1.77
     used
    1.65
     There
    1.56
    Because
    1.54
    hyundai
    1.53
    上がった
    1.49
    ↵↵
    1.48
    At
    1.45
    錚
    1.44
    Activations Density 0.006%

    No Known Activations