© 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. 9251
    Prev
    Next
    INDEX
    Explanations

    academic abbreviations and jargon

    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
    an
    0.83
    т
    0.81
    et
    0.78
    на
    0.77
    1
    0.76
    the
    0.71
    ak
    0.70
    क
    0.70
    я
    0.70
    ка
    0.68
    POSITIVE LOGITS
     Фургала
    0.58
    。"
    0.56
    "。
    0.55
     of
    0.55
    modation
    0.54
     radian
    0.54
    🫰
    0.52
    嗽
    0.52
     점에서
    0.51
     。
    0.51
    Activations Density 0.016%

    No Known Activations