© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 231727
    Prev
    Next
    INDEX
    Explanations

    real flexibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    矢量
    0.48
    пада
    0.48
     ஆண்டுகளில்
    0.46
    蒎
    0.45
    났다
    0.44
    不等
    0.44
    انی
    0.44
     તમા
    0.44
    欹
    0.44
    TIMESTAMP
    0.43
    POSITIVE LOGITS
     otra
    0.49
     confirmation
    0.47
    opens
    0.46
     beautifully
    0.45
     crocodiles
    0.45
     nutritionist
    0.45
     kids
    0.44
     scientists
    0.44
     praises
    0.43
     dialysis
    0.43
    Activations Density 0.000%

    No Known Activations