Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 4820
    Prev
    Next
    INDEX
    Explanations

    mathematical, time, or technical concepts

    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
    腕時計
    0.52
    ологі
    0.47
     دستاویز
    0.44
    هما
    0.44
    נון
    0.43
    Procedure
    0.43
    吋
    0.42
    変更
    0.42
    受賞
    0.42
    annulation
    0.42
    POSITIVE LOGITS
     n
    0.61
    pe
    0.56
     it
    0.55
     match
    0.54
    aya
    0.51
    verb
    0.48
    pl
    0.47
    on
    0.47
    ivil
    0.47
    match
    0.46
    Activations Density 0.000%

    No Known Activations