© 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. 7179
    Prev
    Next
    INDEX
    Explanations

    paper and related materials

    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
    ’
    -2.28
    ">−
    -1.89
    ?’
    -1.88
    d
    -1.78
    ER
    -1.72
    )’
    -1.69
    umacher
    -1.52
    S
    -1.50
     дизе
    -1.50
     wor
    -1.50
    POSITIVE LOGITS
     두
    1.63
    畎
    1.56
    賸
    1.56
     rozwiąz
    1.55
    ouvrir
    1.52
    永遠
    1.51
    appartement
    1.50
     lends
    1.47
    總是
    1.45
     nash
    1.44
    Activations Density 0.013%

    No Known Activations