© 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. 44997
    Prev
    Next
    INDEX
    Explanations

    city, town, ku, county

    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
    </em>
    -1.80
     We
    -1.77
    ۠
    -1.68
    龶
    -1.60
     sebelum
    -1.50
     If
    -1.50
     grounds
    -1.50
    ⸂
    -1.49
    ませんが
    -1.48
    𝙵
    -1.47
    POSITIVE LOGITS
    '
    2.31
    “
    2.28
    谖
    1.88
    </i>
    1.88
    ⤻
    1.82
     erfaren
    1.78
    </h1>
    1.77
     lesquelles
    1.76
     autre
    1.75
    larda
    1.75
    Activations Density 0.005%

    No Known Activations