© 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. 258520
    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
    ח
    0.62
     fragile
    0.47
    ק
    0.46
    ्ह
    0.46
    ברה
    0.46
     refills
    0.44
    חד
    0.44
    闱
    0.43
     tubular
    0.43
    гӀ
    0.43
    POSITIVE LOGITS
    🏴
    0.52
     Speech
    0.50
     geboren
    0.48
     ภาษา
    0.47
     文字
    0.46
     Catholic
    0.45
     FEEL
    0.45
     Nonlinear
    0.45
     Belief
    0.45
     مك
    0.44
    Activations Density 0.001%

    No Known Activations