© 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. 254442
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     längre
    0.48
    velocityY
    0.44
    ⅓
    0.43
    ٹنے
    0.42
    lang
    0.42
     शुक्रवार
    0.41
    carbon
    0.41
     numerosas
    0.40
    «
    0.40
    tang
    0.39
    POSITIVE LOGITS
     MODKEY
    0.51
     または
    0.48
     програм
    0.48
     ח
    0.47
    ೋಪ
    0.47
     アクセ
    0.46
    ወት
    0.46
    дора
    0.46
    츤
    0.46
    ק
    0.46
    Activations Density 0.001%

    No Known Activations