© 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. 200160
    Prev
    Next
    INDEX
    Explanations

    do or perform tasks

    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
    つ
    0.54
     тай
    0.47
    <0x80>
    0.46
     که
    0.45
     журнали
    0.45
     indemnity
    0.45
    盥
    0.45
    а
    0.44
    ሀ
    0.43
    ๅ
    0.43
    POSITIVE LOGITS
     Gill
    0.47
     einigen
    0.46
     Udd
    0.46
     einige
    0.44
     Aaron
    0.44
     arit
    0.44
     unor
    0.43
    ήμερα
    0.43
     Adam
    0.43
     Ferrer
    0.43
    Activations Density 0.006%

    No Known Activations