© 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. 123514
    Prev
    Next
    INDEX
    Explanations

    similarity and vibe check

    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
    '
    0.55
    ic
    0.47
    Salt
    0.46
    .,
    0.46
    #
    0.45
    Von
    0.45
    mce
    0.44
    Late
    0.44
    Чем
    0.43
    {
    0.43
    POSITIVE LOGITS
     ಯಾರ
    0.48
     தே
    0.47
    вання
    0.47
     ಸ
    0.47
    नीय
    0.46
     patted
    0.46
     कपिल
    0.46
    虢
    0.45
     downloadable
    0.45
     Stéphane
    0.45
    Activations Density 0.000%

    No Known Activations