© 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. 143628
    Prev
    Next
    INDEX
    Explanations

    picture palms

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    cett
    0.52
     LDGs
    0.51
     ၊
    0.47
    ⎮
    0.47
     фонд
    0.46
     আৰু
    0.45
     Astor
    0.44
    ورت
    0.44
     Equitable
    0.43
    掌握
    0.43
    POSITIVE LOGITS
    Y
    0.51
    S
    0.50
    T
    0.50
    H
    0.50
    Я
    0.48
    service
    0.47
    U
    0.46
    ও
    0.46
     blackened
    0.46
    N
    0.46
    Activations Density 0.000%

    No Known Activations