© 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. 38485
    Prev
    Next
    INDEX
    Explanations

    how and why questions

    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
    !!!!!!!!!
    -0.85
    unfortunately
    -0.84
    adalah
    -0.83
     retinol
    -0.82
     Análisis
    -0.81
     souverain
    -0.81
     Función
    -0.79
     salic
    -0.79
    unknown
    -0.79
     chaîne
    -0.79
    POSITIVE LOGITS
     why
    1.29
     even
    1.05
     gets
    1.02
     Why
    0.97
     each
    0.93
     incluso
    0.92
    Why
    0.90
    Dlaczego
    0.90
     mengapa
    0.90
    Почему
    0.90
    Activations Density 0.064%

    No Known Activations