© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 50607
    Prev
    Next
    INDEX
    Explanations

    gills and biological features

    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
    Experimental
    0.46
     |,
    0.43
     Experimental
    0.41
     دانشگاه
    0.41
     |
    0.39
     Diam
    0.39
     ,
    0.39
    已经
    0.38
     বিশ্ববিদ্যাল
    0.38
     Paintings
    0.38
    POSITIVE LOGITS
     disb
    0.47
    ákat
    0.46
    鈳
    0.45
     perched
    0.44
     της
    0.43
     المراجعه
    0.43
     queued
    0.42
     paycheck
    0.42
     billed
    0.41
    們
    0.41
    Activations Density 0.001%

    No Known Activations