© 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. 99389
    Prev
    Next
    INDEX
    Explanations

    point blank range

    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
    ↔
    -0.73
    stool
    -0.73
    monger
    -0.72
    elaar
    -0.69
     न
    -0.69
    ̌
    -0.69
     DIO
    -0.68
    ulier
    -0.68
    IMENT
    -0.66
     lenger
    -0.66
    POSITIVE LOGITS
     point
    3.16
     flat
    2.48
    point
    2.47
    Point
    2.25
     Point
    2.19
     POINT
    2.11
    flat
    2.02
    POINT
    1.92
    Flat
    1.69
     outright
    1.62
    Activations Density 0.080%

    No Known Activations