© 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. 257581
    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
    ți
    0.51
     =
    0.49
    명이
    0.49
    ns
    0.47
    <unused2221>
    0.45
    shaped
    0.45
    lname
    0.43
    findung
    0.43
    ocity
    0.42
    عبة
    0.41
    POSITIVE LOGITS
     reforms
    0.50
     scripts
    0.46
     sektor
    0.46
    嫒
    0.45
    搛
    0.44
    𝑰
    0.44
     formate
    0.44
     gels
    0.43
     Shankar
    0.43
     फस
    0.43
    Activations Density 0.002%

    No Known Activations