© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 107969
    Prev
    Next
    INDEX
    Explanations

    explaining why, questions, play

    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
     AGRICULTURAL
    0.46
    Bacteria
    0.45
    ስቃሴ
    0.45
     bacterias
    0.44
     населення
    0.44
    犃
    0.44
    िफिशियल
    0.43
    katore
    0.43
    ())),
    0.43
     オール
    0.43
    POSITIVE LOGITS
    ten
    0.48
    m
    0.46
    t
    0.46
    ren
    0.46
    iTunes
    0.44
    covers
    0.44
    is
    0.43
    rock
    0.41
    illus
    0.41
    空的
    0.41
    Activations Density 0.018%

    No Known Activations