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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 168743
    Prev
    Next
    INDEX
    Explanations

    information processing and analysis

    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
     전에
    0.43
    арма
    0.41
    暐
    0.41
    对他
    0.41
     Gre
    0.39
     journalism
    0.39
    గా
    0.38
    보니
    0.38
     tendrás
    0.37
     Ру
    0.36
    POSITIVE LOGITS
     kautta
    0.48
    rification
    0.46
    रिडोर
    0.46
    bidden
    0.45
    kis
    0.45
    io
    0.45
    inggi
    0.45
     samping
    0.44
    \_
    0.44
    isiert
    0.43
    Activations Density 0.006%

    No Known Activations