© 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. 34-GEMMASCOPE-RES-131K
    7. 106746
    Prev
    Next
    INDEX
    Explanations

    string type declarations

    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_34/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
     Jüng
    -0.98
     them
    -0.97
    Zubereitung
    -0.96
    口感
    -0.94
    才可以
    -0.91
    Those
    -0.90
    Herkunft
    -0.89
    Materiál
    -0.89
    ・・。
    -0.89
    Výhody
    -0.88
    POSITIVE LOGITS
     String
    1.83
     string
    1.61
    String
    1.52
     strings
    1.45
     Stringer
    1.21
     QString
    1.18
    字符串
    1.13
    STRING
    1.09
    惊艳
    1.09
    drawString
    1.08
    Activations Density 0.022%

    No Known Activations