© 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. 57497
    Prev
    Next
    INDEX
    Explanations

    version numbers

    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
     nyingi
    -0.75
     individu
    -0.73
     Frem
    -0.72
    Packing
    -0.71
     Dogecoin
    -0.69
    Center
    -0.69
    MAR
    -0.68
    缓存
    -0.68
    Fra
    -0.67
     Centers
    -0.67
    POSITIVE LOGITS
    Galax
    0.68
    丫头
    0.68
    Occasion
    0.68
     ответить
    0.68
    UserRole
    0.67
    Galactic
    0.66
    ukov
    0.65
     servant
    0.65
     στα
    0.63
     hånd
    0.63
    Activations Density 0.076%

    No Known Activations