© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3591
    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
     പറയ
    0.53
     næ
    0.51
     yüz
    0.50
     Им
    0.50
    MW
    0.49
     Beispiele
    0.49
    戛
    0.49
    <unused266>
    0.49
     Mene
    0.48
     opaque
    0.48
    POSITIVE LOGITS
    der
    0.52
     trocar
    0.48
    zinger
    0.47
    s
    0.47
    court
    0.47
    du
    0.46
    struck
    0.46
    php
    0.45
    0
    0.44
    ao
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.