© 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. 65771
    Prev
    Next
    INDEX
    Explanations

    code structure and specific titles

    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
    蚰
    -1.38
    familien
    -1.35
    蟶
    -1.35
    hlar
    -1.35
    ième
    -1.34
    signable
    -1.34
    corbic
    -1.30
    baren
    -1.27
    tipps
    -1.27
    signee
    -1.27
    POSITIVE LOGITS
    </b>
    1.48
     different
    1.48
    1.30
    -
    1.27
     Different
    1.27
    _
    1.24
    ka
    1.23
     M
    1.21
    '
    1.19
    L
    1.18
    Activations Density 0.000%

    No Known Activations