© 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. 22-GEMMASCOPE-RES-131K
    7. 27185
    Prev
    Next
    INDEX
    Explanations

    XML and JavaScript code

    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
     to
    -1.38
     from
    -1.20
     one
    -1.06
    に行ってきました
    -0.95
    gunakan
    -0.93
    providedIn
    -0.91
    ätzung
    -0.90
    onyme
    -0.90
    鉗
    -0.88
     игрушки
    -0.83
    POSITIVE LOGITS
    ﾒ
    1.23
    把她
    1.10
     laguna
    1.09
     miejsco
    1.04
     diría
    1.03
     milano
    1.02
     buro
    1.01
    ‌.
    1.00
    特意
    0.99
     jemand
    0.99
    Activations Density 0.005%

    No Known Activations