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. 31-GEMMASCOPE-2-RES-16K
    4. 12610
    Prev
    Next
    INDEX
    Explanations

    read, parse

    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
     പ്രതിഷേധ
    0.47
    वते
    0.46
     caz
    0.46
     disenfranch
    0.46
    大學
    0.45
     incentiv
    0.44
    鄴
    0.44
     rightfully
    0.43
     incentivize
    0.43
    كب
    0.42
    POSITIVE LOGITS
    s
    0.50
    indel
    0.47
    ile
    0.46
    ind
    0.45
    il
    0.44
    es
    0.43
    and
    0.43
    ard
    0.43
    虽然
    0.43
    aun
    0.42
    Activations Density 0.008%

    No Known Activations