© 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. 2927
    Prev
    Next
    INDEX
    Explanations

    cryptographic keys

    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
     Mela
    -0.78
    ạp
    -0.75
     Public
    -0.75
    噶
    -0.73
    Guang
    -0.73
     лег
    -0.73
    婧
    -0.70
     ICollection
    -0.69
    PublicKey
    -0.69
    читал
    -0.69
    POSITIVE LOGITS
    SAN
    0.82
    usages
    0.81
    videoId
    0.77
     Ն
    0.77
     key
    0.77
    Et
    0.77
     SAN
    0.75
    key
    0.75
     turntable
    0.75
    Key
    0.74
    Activations Density 0.058%

    No Known Activations