© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 227911
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     embodied
    0.42
    šk
    0.41
    h
    0.40
    ミリー
    0.40
     hasher
    0.40
    τη
    0.40
     verdiği
    0.40
    undred
    0.40
    versive
    0.40
    radu
    0.39
    POSITIVE LOGITS
     знают
    0.46
     আস্তে
    0.43
     lavorare
    0.43
    旁边
    0.42
     flujo
    0.42
     entice
    0.42
     posible
    0.41
    诖
    0.41
     появляется
    0.41
    不了
    0.40
    Activations Density 0.002%

    No Known Activations