© 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. 253262
    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
     seabed
    0.56
    ću
    0.52
    蜼
    0.52
    Ｂ
    0.51
     crayfish
    0.50
     shogun
    0.50
     aided
    0.49
     sewers
    0.49
    鴎
    0.49
    SII
    0.49
    POSITIVE LOGITS
    。
    0.51
    د
    0.48
    ↵
    0.48
    </h5>
    0.47
    ata
    0.47
    ിലുള്ള
    0.43
    това
    0.42
    Fitz
    0.41
    communities
    0.41
    known
    0.40
    Activations Density 0.000%

    No Known Activations