© 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-65K
    7. 56383
    Prev
    Next
    INDEX
    Explanations

    universally understood

    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_65k_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
    ,
    0.53
    $.
    0.50
    s
    0.48
    ities
    0.46
     (
    0.45
     for
    0.42
     fake
    0.42
    ។
    0.41
    ala
    0.41
     ($
    0.41
    POSITIVE LOGITS
    線
    0.48
    मर्रा
    0.48
    ώς
    0.47
    ስቃሴ
    0.46
    χη
    0.44
    メタ
    0.44
    я
    0.44
     সুভাষ
    0.43
    яс
    0.43
     cucumbers
    0.43
    Activations Density 0.002%

    No Known Activations