© 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. 28387
    Prev
    Next
    INDEX
    Explanations

    OEM license

    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
    镳
    0.46
    gave
    0.43
    bank
    0.43
    optimize
    0.42
     participer
    0.42
     and
    0.42
    oder
    0.42
    リット
    0.42
    agger
    0.42
     partecipare
    0.41
    POSITIVE LOGITS
    ని
    0.52
    सूर्य
    0.52
    望
    0.50
    穸
    0.46
    થે
    0.44
     FILTER
    0.44
     LOOP
    0.44
     Uranus
    0.44
     Neurology
    0.43
     ROLE
    0.43
    Activations Density 0.000%

    No Known Activations