© 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. 129414
    Prev
    Next
    INDEX
    Explanations

    closing preprocessor directives

    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
    -2.77
     poniendo
    -2.02
     Также
    -1.96
     reklama
    -1.93
     також
    -1.90
    providedIn
    -1.88
     Also
    -1.88
     También
    -1.87
     stalo
    -1.87
     Gemeinsame
    -1.82
    POSITIVE LOGITS
    它
    1.89
    u
    1.88
    ↵
    1.81
    唧
    1.69
    d
    1.68
     её
    1.63
    s
    1.63
    作为一个
    1.61
    それは
    1.61
    ють
    1.61
    Activations Density 0.003%

    No Known Activations