© 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. 22-GEMMASCOPE-RES-131K
    7. 25440
    Prev
    Next
    INDEX
    Explanations

    code delimiters and string methods

    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_22/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
    isations
    -1.09
    ができます
    -1.07
    Produzione
    -1.03
    gangss
    -1.02
     Mallorca
    -0.93
     baile
    -0.93
    artet
    -0.91
    žití
    -0.88
     Pob
    -0.87
     bada
    -0.87
    POSITIVE LOGITS
    有力
    0.91
     name
    0.87
    形成了
    0.86
     looking
    0.79
     too
    0.78
     representatives
    0.77
    ということです
    0.77
     single
    0.77
     dziecka
    0.77
    ということを
    0.77
    Activations Density 0.003%

    No Known Activations