© 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. 253166
    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
    防护
    0.48
    m
    0.48
     podcast
    0.47
    赵
    0.47
    发育
    0.47
    م
    0.46
     Laura
    0.45
    顾
    0.45
     Gabrielle
    0.44
     supportive
    0.43
    POSITIVE LOGITS
     นี่
    0.52
    StartTime
    0.52
    FIELDS
    0.52
    EVENTS
    0.52
    ChangeString
    0.51
     کامیابی
    0.51
    ANSWER
    0.50
     ಸ್ಥ
    0.50
    SERVIDOR
    0.50
     مقدار
    0.49
    Activations Density 0.002%

    No Known Activations