© 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. 4787
    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
    MathMarks
    0.55
     الموا
    0.52
     ایش
    0.51
    ᵃ
    0.48
     soğ
    0.47
    চ্ছেন
    0.47
     elektri
    0.46
    িক
    0.46
     ロゴ
    0.46
     электронной
    0.45
    POSITIVE LOGITS
    2
    0.56
    adies
    0.50
    1
    0.49
    eca
    0.46
     Prozent
    0.46
    pern
    0.46
    分類
    0.46
     Levin
    0.46
     defe
    0.46
    多
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.