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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 1674
    Prev
    Next
    INDEX
    Explanations

    specialized capitalized words

    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_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
     of
    0.24
     A
    0.22
    k
    0.22
    0
    0.22
     Science
    0.21
     Genres
    0.21
     Wissenschaft
    0.21
     anderes
    0.21
     We
    0.21
     Messrs
    0.21
    POSITIVE LOGITS
    ™
    0.25
    的
    0.25
    에
    0.24
     ју
    0.24
    echolog
    0.24
    TM
    0.23
    тың
    0.23
    의
    0.23
    必須
    0.23
    ovať
    0.22
    Activations Density 0.509%

    No Known Activations