© 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. 107851
    Prev
    Next
    INDEX
    Explanations

    licensed under the license

    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
     článku
    -0.75
    lijker
    -0.74
    chede
    -0.74
     emigration
    -0.73
    Exports
    -0.73
    fferty
    -0.73
    ழ
    -0.72
     lever
    -0.70
    minister
    -0.69
    ytick
    -0.69
    POSITIVE LOGITS
     César
    0.72
    folding
    0.66
     smaak
    0.63
     peinados
    0.61
    兑
    0.60
    extras
    0.60
    dulos
    0.60
     através
    0.60
     contratto
    0.60
    utel
    0.59
    Activations Density 0.069%

    No Known Activations