© 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. 100095
    Prev
    Next
    INDEX
    Explanations

    lists, when, cycle, psychiatrists, thesis, needs, AI

    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
    інки
    0.57
     снима
    0.57
    .".,
    0.55
    .",[
    0.54
     vudd
    0.54
    醐
    0.54
    𒅗
    0.54
    OrderFlight
    0.53
     化粧
    0.53
     sillonné
    0.53
    POSITIVE LOGITS
     a
    0.55
    D
    0.55
     are
    0.55
     be
    0.54
    en
    0.53
    sh
    0.50
     tumble
    0.48
    ar
    0.47
    {
    0.47
    \
    0.47
    Activations Density 0.000%

    No Known Activations