© 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. 40-GEMMASCOPE-2-RES-262K
    7. 99787
    Prev
    Next
    INDEX
    Explanations

    Bayesian model averaging

    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_40_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
    $('
    0.37
    Critics
    0.36
     bő
    0.36
    Investment
    0.35
     चांदनी
    0.35
    بيق
    0.34
    дей
    0.34
    porque
    0.34
    jahr
    0.33
     zhī
    0.33
    POSITIVE LOGITS
     Waco
    0.62
     Baylor
    0.54
     갖
    0.43
     bearing
    0.43
    ൽപ്പ
    0.42
     Sic
    0.41
    拼接
    0.40
     Bearing
    0.39
     Seamless
    0.39
     Route
    0.38
    Activations Density 0.004%

    No Known Activations