© 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. 6377
    Prev
    Next
    INDEX
    Explanations

    the start of words like B, Bi, or B-

    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
    л
    1.30
    ل
    1.29
     by
    1.28
    ש
    1.23
    ל
    1.13
     as
    1.11
    n
    1.10
    в
    1.03
    by
    1.02
    น
    1.02
    POSITIVE LOGITS
    <0x91>
    0.91
    ция
    0.91
     जिसके
    0.88
    2
    0.87
    jamin
    0.83
    য়া
    0.82
    kort
    0.80
    ิก
    0.79
    ৭১
    0.77
    ន៍
    0.74
    Activations Density 0.541%

    No Known Activations