© 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. 66587
    Prev
    Next
    INDEX
    Explanations

    implementing interfaces

    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
     Había
    -1.03
     budete
    -1.03
     talvez
    -1.02
     TAMBIÉN
    -0.99
    Смотрите
    -0.98
     AÑOS
    -0.96
     Também
    -0.95
     musíte
    -0.95
    踊り
    -0.95
     настройки
    -0.94
    POSITIVE LOGITS
     Accesat
    0.89
     msec
    0.89
     osa
    0.89
     בין
    0.86
     manages
    0.86
     trying
    0.85
     cung
    0.85
     egen
    0.85
    hoch
    0.84
     managing
    0.84
    Activations Density 0.002%

    No Known Activations