© 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. 26504
    Prev
    Next
    INDEX
    Explanations

    PHP script execution

    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
    hrungen
    -1.13
     if
    -1.04
    borgen
    -0.98
    ıy
    -0.98
                                 
    -0.97
    ถ้า
    -0.96
    IRT
    -0.96
    пион
    -0.96
    oacute
    -0.95
    💭
    -0.95
    POSITIVE LOGITS
     Daß
    1.08
     Ähnliche
    1.02
     organisiert
    1.00
     Detalles
    0.98
    🩱
    0.95
     énorm
    0.94
    𝒙
    0.94
     ontem
    0.93
     yesterday
    0.92
     będę
    0.92
    Activations Density 0.022%

    No Known Activations