© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1319
    Prev
    Next
    INDEX
    Explanations

    cz import

    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
    vron
    -0.89
    GIVEREF
    -0.84
    cellor
    -0.84
    ℅
    -0.82
     dibangun
    -0.82
    ouren
    -0.81
    hanna
    -0.81
    cidae
    -0.81
    мят
    -0.80
    øg
    -0.80
    POSITIVE LOGITS
     它
    0.83
    ł
    0.81
    咳咳
    0.81
    abetta
    0.80
     a
    0.79
     vooral
    0.79
    í
    0.78
    meyer
    0.78
     soprattutto
    0.77
    zt
    0.76
    Activations Density 0.002%

    No Known Activations