© 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-65K
    7. 13991
    Prev
    Next
    INDEX
    Explanations

    ideas, trends, community, and data

    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_65k_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
    Х
    0.54
     mês
    0.50
    Μ
    0.50
    લ
    0.50
     WIND
    0.47
    Τ
    0.47
    \]
    0.46
     mię
    0.46
    пан
    0.46
    ந
    0.46
    POSITIVE LOGITS
     toasted
    0.46
     delegate
    0.46
    toISO
    0.46
     popped
    0.45
     scrim
    0.45
    asă
    0.43
     peered
    0.43
    ak
    0.42
    eer
    0.42
    orske
    0.42
    Activations Density 0.012%

    No Known Activations