© 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. 138159
    Prev
    Next
    INDEX
    Explanations

    wikilinks

    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
    <0x80>
    0.84
    d
    0.71
    t
    0.69
    c
    0.63
     NVIC
    0.60
    il
    0.54
    ut
    0.54
     DO
    0.54
    ning
    0.52
     IS
    0.52
    POSITIVE LOGITS
     coração
    0.69
     dormitorio
    0.68
     intestino
    0.67
     schist
    0.67
     herpes
    0.65
     écriv
    0.63
     autobus
    0.63
     சுண்ணாம்பு
    0.63
    력
    0.62
     escritos
    0.61
    Activations Density 0.001%

    No Known Activations