© 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. 30310
    Prev
    Next
    INDEX
    Explanations

    programmatic structures and parameters

    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
     SDR
    -0.76
    cane
    -0.73
     Marketplace
    -0.69
     Steam
    -0.66
    成都
    -0.66
     opened
    -0.66
    HPP
    -0.65
     Clement
    -0.63
     Derrick
    -0.63
     być
    -0.62
    POSITIVE LOGITS
     sky
    0.72
    alat
    0.67
    їна
    0.66
    ITTLE
    0.66
    strncmp
    0.65
    Pile
    0.64
     Arian
    0.64
     Mississauga
    0.63
    tellungen
    0.63
    наче
    0.62
    Activations Density 0.034%

    No Known Activations