© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9786
    Prev
    Next
    INDEX
    Explanations

    character encoding

    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_16k_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
    g
    0.63
    d
    0.54
    el
    0.54
    er
    0.52
    k
    0.50
    t
    0.49
    y
    0.49
    en
    0.47
    ina
    0.47
    s
    0.46
    POSITIVE LOGITS
    エス
    0.49
     capables
    0.49
    虧
    0.47
    人數
    0.47
     obligatorio
    0.46
     tư
    0.45
    يت
    0.45
     مە
    0.45
     acteurs
    0.45
     estratégico
    0.45
    Activations Density 0.097%

    No Known Activations