© 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. 17974
    Prev
    Next
    INDEX
    Explanations

    components and economy

    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
    ка
    0.50
    ﮐ
    0.45
    ان
    0.45
    Ан
    0.43
    кон
    0.43
    ин
    0.41
    зы
    0.40
    з
    0.40
    لز
    0.40
    ร
    0.40
    POSITIVE LOGITS
     embell
    0.45
     adept
    0.43
    ことにより
    0.43
     fortement
    0.42
    తులను
    0.42
     axonal
    0.42
    ere
    0.42
    âteaux
    0.41
     arrhyth
    0.41
     overrated
    0.41
    Activations Density 0.000%

    No Known Activations