© 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. 65878
    Prev
    Next
    INDEX
    Explanations

    mathematical notation symbols

    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
     подойдет
    -0.90
     sehen
    -0.89
     dzień
    -0.84
     IBOutlet
    -0.84
     informó
    -0.82
     creó
    -0.82
     Ленина
    -0.82
    汙
    -0.81
     погре
    -0.81
    articles
    -0.81
    POSITIVE LOGITS
    arjo
    0.93
     siff
    0.92
     spire
    0.92
     Dica
    0.91
     raja
    0.91
    "]))
    0.90
     reigning
    0.89
    Observation
    0.88
     Ringo
    0.88
    __.__
    0.87
    Activations Density 0.014%

    No Known Activations