© 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. 48524
    Prev
    Next
    INDEX
    Explanations

    state cross examines

    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
    吩
    -0.79
     فرش
    -0.75
    Pautan
    -0.74
     rendez
    -0.73
     carburant
    -0.71
    嘮
    -0.71
    ulturen
    -0.69
    oltà
    -0.69
     näky
    -0.69
    满足
    -0.68
    POSITIVE LOGITS
     cross
    2.44
    cross
    1.77
    Cross
    1.65
     cros
    1.65
     Cross
    1.63
     examination
    1.55
     questioning
    1.41
     CROSS
    1.27
    examination
    1.23
     questions
    1.20
    Activations Density 0.017%

    No Known Activations