© 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. 4233
    Prev
    Next
    INDEX
    Explanations

    computer hardware components

    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
    あるいは
    0.39
     ឬ
    0.38
    PMorgan
    0.36
     einzigen
    0.36
     sırasında
    0.35
    व्यापी
    0.34
    又は
    0.33
     dispel
    0.33
     perpend
    0.33
     arba
    0.33
    POSITIVE LOGITS
    लेट
    0.42
     and
    0.42
    及
    0.40
    本体
    0.39
    新
    0.39
     And
    0.39
     that
    0.37
     समेत
    0.36
     и
    0.36
     supplier
    0.36
    Activations Density 0.054%

    No Known Activations