© 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. 58087
    Prev
    Next
    INDEX
    Explanations

    XML schemas, data contracts, and annotations

    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
    idens
    -0.96
    andan
    -0.81
    OMON
    -0.80
    жня
    -0.79
    CHLOR
    -0.77
    Adverten
    -0.77
     جمعه
    -0.76
     samurai
    -0.76
     покра
    -0.75
     egreg
    -0.74
    POSITIVE LOGITS
     required
    1.04
     wanted
    0.92
     demanded
    0.88
    使命
    0.84
     propOrder
    0.81
     namespace
    0.81
    רא
    0.80
    тари
    0.77
     also
    0.76
     petróleo
    0.75
    Activations Density 0.002%

    No Known Activations