© 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. 41151
    Prev
    Next
    INDEX
    Explanations

    magnets, attract, repel

    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
    鎳
    0.46
     Smiley
    0.46
    奶
    0.43
    Nord
    0.42
    美
    0.42
    克
    0.42
     cigarette
    0.41
     почти
    0.41
    巧克力
    0.41
    乳
    0.40
    POSITIVE LOGITS
     stabilise
    0.45
     preclude
    0.44
     loses
    0.44
    same
    0.44
    leti
    0.44
     stabilize
    0.44
     evacuate
    0.44
    lose
    0.43
    સ્થા
    0.43
    bbero
    0.43
    Activations Density 0.002%

    No Known Activations