© 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. 15835
    Prev
    Next
    INDEX
    Explanations

    legal hearing

    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
     and
    -1.11
    гает
    -1.06
     salas
    -1.06
     velas
    -1.06
    стит
    -1.05
    ResumeLayout
    -1.03
     lás
    -1.02
    )}{
    -1.02
    ครื่อง
    -1.02
    鏌
    -1.01
    POSITIVE LOGITS
    C
    1.16
    c
    1.14
    N
    1.13
    n
    1.13
    x
    1.10
    w
    1.05
    X
    1.03
    D
    1.02
    H
    1.02
    O
    1.01
    Activations Density 0.031%

    No Known Activations