© 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. 16-GEMMASCOPE-2-RES-262K
    7. 13590
    Prev
    Next
    INDEX
    Explanations

    liberal arts, asymptotes

    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_16_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
    حی
    0.65
    ана
    0.64
    の変化
    0.59
    ین
    0.58
    urangi
    0.58
    うまく
    0.58
    ی
    0.57
    니
    0.56
    연출
    0.55
    レンタ
    0.55
    POSITIVE LOGITS
    ↵↵
    0.61
     casket
    0.59
     spring
    0.58
     jogging
    0.58
     galley
    0.58
     a
    0.57
     motel
    0.57
     mezzanine
    0.57
     carton
    0.56
    a
    0.56
    Activations Density 0.001%

    No Known Activations