© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 14469
    Prev
    Next
    INDEX
    Explanations

    temple complex

    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
    та
    0.72
     realizzazione
    0.68
    ة
    0.65
    ing
    0.63
     rehabilitación
    0.63
     riconoscimento
    0.61
    のと
    0.60
    тат
    0.60
    .¹
    0.58
     riduzione
    0.58
    POSITIVE LOGITS
    N
    0.73
    M
    0.70
     from
    0.68
    L
    0.67
    R
    0.64
    [
    0.64
    G
    0.63
     Days
    0.63
    $
    0.61
    Mar
    0.60
    Activations Density 0.001%

    No Known Activations