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. 16-GEMMASCOPE-2-RES-262K
    4. 109535
    Prev
    Next
    INDEX
    Explanations

    standard deviation

    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_16_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
    ية
    0.68
    ด
    0.68
     wybra
    0.66
     ballad
    0.65
     ให้
    0.64
    ى
    0.63
     sebum
    0.62
     włas
    0.62
     wzrost
    0.62
    ல்
    0.61
    POSITIVE LOGITS
    g
    0.67
    the
    0.63
    active
    0.55
    0
    0.55
    error
    0.55
    soph
    0.55
    great
    0.54
    Localization
    0.54
    i
    0.54
    G
    0.53
    Activations Density 0.006%

    No Known Activations