© 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. 1113
    Prev
    Next
    INDEX
    Explanations

    or, of, to, in, from

    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
     viciss
    0.35
     dificuldade
    0.34
     ત્રણ
    0.33
     dificultad
    0.33
     exuber
    0.32
    ཋ
    0.32
     insurgency
    0.32
     redness
    0.32
    热情
    0.32
     két
    0.31
    POSITIVE LOGITS
     அல்லது
    0.42
     ឬ
    0.40
     your
    0.40
    或
    0.39
     any
    0.39
    ，
    0.38
     অথবা
    0.37
     or
    0.37
     gesamten
    0.37
     কিংবা
    0.36
    Activations Density 0.235%

    No Known Activations