© 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. 48633
    Prev
    Next
    INDEX
    Explanations

    versions, dates, and identifiers

    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
     Obama
    -1.07
    Obama
    -0.97
     Wii
    -0.94
     Sochi
    -0.84
     KK
    -0.82
     epo
    -0.81
     Kj
    -0.80
     Barack
    -0.79
     Valkyrie
    -0.78
     Cooked
    -0.76
    POSITIVE LOGITS
     Entwurf
    0.77
    TikTok
    0.76
    こと
    0.76
    ظم
    0.74
    事
    0.73
     alemão
    0.71
     Touristen
    0.71
    建议
    0.71
     Architektur
    0.71
     Konstruktion
    0.70
    Activations Density 0.160%

    No Known Activations