© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103847
    Prev
    Next
    INDEX
    Explanations

    hey

    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
    ه
    -1.77
     untuk
    -1.72
     pisze
    -1.69
    </sub>
    -1.59
    pakah
    -1.54
     prøve
    -1.53
    ㅂ
    -1.47
     lakini
    -1.46
    蔸
    -1.45
    ↑↑↑</
    -1.45
    POSITIVE LOGITS
     If
    1.63
     quelle
    1.63
    leno
    1.57
    寄り
    1.55
    Compared
    1.55
    If
    1.52
     autant
    1.48
    ジュン
    1.48
     мамы
    1.46
     don
    1.45
    Activations Density 0.003%

    No Known Activations