© 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. 41745
    Prev
    Next
    INDEX
    Explanations

    concepts around numbers, actions, and states

    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
    n
    0.44
    VER
    0.43
    אם
    0.43
    रक
    0.43
    Архи
    0.42
    К
    0.42
    ftime
    0.41
     DESCRIPTION
    0.41
    Ft
    0.41
    ICKEL
    0.41
    POSITIVE LOGITS
     Gesundheit
    0.45
     entitled
    0.45
     행동
    0.42
     힘들
    0.42
     constituted
    0.41
    maier
    0.41
     кок
    0.41
     qualitatively
    0.41
     marginalised
    0.41
     以
    0.40
    Activations Density 0.002%

    No Known Activations