© 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. 40817
    Prev
    Next
    INDEX
    Explanations

    challenging assumptions

    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
    toys
    0.43
    fert
    0.42
    tact
    0.42
    狂
    0.41
    arete
    0.41
     моя
    0.41
     фрук
    0.40
    scht
    0.40
    retro
    0.40
     کمپیو
    0.40
    POSITIVE LOGITS
     anche
    0.49
     dotyczące
    0.48
     related
    0.48
     hver
    0.47
    อัน
    0.46
    寢
    0.46
     związane
    0.45
     bộ
    0.44
    ।*
    0.44
    녀
    0.44
    Activations Density 0.003%

    No Known Activations