© 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. 22-GEMMASCOPE-RES-131K
    7. 72048
    Prev
    Next
    INDEX
    Explanations

    around the corner

    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_22/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
    恹
    -1.00
    irical
    -0.98
    ⚌
    -0.96
    ographic
    -0.96
    flatMap
    -0.94
     idyllic
    -0.94
     วิ
    -0.93
     kän
    -0.92
    ledem
    -0.92
    unno
    -0.91
    POSITIVE LOGITS
     especially
    1.09
     with
    1.09
     that
    1.05
     several
    1.04
     or
    1.02
     crazy
    0.95
     on
    0.94
    그리고
    0.90
     three
    0.90
     soprattutto
    0.88
    Activations Density 0.001%

    No Known Activations