© 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. 14259
    Prev
    Next
    INDEX
    Explanations

    credit cards

    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
     Redacción
    -1.08
    ſten
    -1.06
    ﾐ
    -1.06
     „
    -1.06
     }}^{\
    -1.04
    昨
    -1.01
     Reſ
    -1.00
    」,
    -0.97
     $($
    -0.97
    ſtre
    -0.96
    POSITIVE LOGITS
     крайней
    0.95
     يون
    0.93
     тысяч
    0.91
    шні
    0.91
    けれ
    0.91
    грі
    0.91
     jų
    0.87
    чені
    0.86
     exceso
    0.85
     introduit
    0.85
    Activations Density 0.053%

    No Known Activations