© 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. 35334
    Prev
    Next
    INDEX
    Explanations

    code documentation and multilingual terms

    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
     homicidio
    -1.00
    
    -1.00
     ministros
    -0.99
     Tomaten
    -0.93
     Dijo
    -0.93
    アクセント
    -0.91
     ।
    -0.90
     noin
    -0.89
     Kartoffeln
    -0.88
     odc
    -0.88
    POSITIVE LOGITS
     suscit
    1.38
    Beskrivelse
    1.28
    Transk
    1.23
     می‌کن
    1.19
    Twee
    1.08
    Destin
    1.07
     nigdy
    1.06
     methodical
    1.06
    Goed
    1.05
     باشی
    1.05
    Activations Density 0.044%

    No Known Activations