© 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. 34-GEMMASCOPE-RES-131K
    7. 77096
    Prev
    Next
    INDEX
    Explanations

    poke, pokémon, poker, poking, poked

    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
     ог
    -0.83
     ober
    -0.73
    Gee
    -0.71
    Brackets
    -0.70
     Lest
    -0.70
    統一
    -0.69
    外人
    -0.68
    sendRequest
    -0.68
     almonds
    -0.66
    Switching
    -0.66
    POSITIVE LOGITS
     pok
    1.13
     Pok
    1.01
    pok
    0.91
    Pok
    0.84
    chés
    0.83
    weed
    0.80
    لوب
    0.79
     EVIDENCE
    0.78
    allus
    0.76
    ליון
    0.76
    Activations Density 0.022%

    No Known Activations