© 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. 244768
    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
     Jesuit
    0.45
     Gaut
    0.42
    沇
    0.41
     trate
    0.41
     Potomac
    0.41
     eponymous
    0.41
     ip
    0.40
     Jefferson
    0.40
     radioactive
    0.40
     Jokowi
    0.40
    POSITIVE LOGITS
    D
    0.65
    ກ
    0.62
    도
    0.57
    G
    0.57
    A
    0.56
    ก
    0.55
    До
    0.53
    บ
    0.52
    B
    0.51
    до
    0.49
    Activations Density 0.000%

    No Known Activations