© 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. 15341
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

    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
    innerWidth
    -1.01
     its
    -0.93
    estus
    -0.92
    tifications
    -0.86
     type
    -0.85
     geschickt
    -0.85
    aabb
    -0.85
    thodes
    -0.85
     it
    -0.83
     variant
    -0.83
    POSITIVE LOGITS
     осно
    0.91
     darb
    0.91
    ük
    0.88
    ORUM
    0.87
    Доброго
    0.85
    Déc
    0.84
    Directeur
    0.83
    HSC
    0.82
    kę
    0.82
     فار
    0.82
    Activations Density 0.013%

    No Known Activations