© 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. 9739
    Prev
    Next
    INDEX
    Explanations

    while... on

    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
     kaisi
    0.42
    тын
    0.41
     rhs
    0.41
    +{
    0.41
     zis
    0.40
     heal
    0.40
    انیه
    0.40
     emuls
    0.40
     siapa
    0.39
     maupun
    0.38
    POSITIVE LOGITS
     bothers
    0.41
     मई
    0.40
     Unable
    0.40
    楨
    0.40
     Están
    0.40
    音频
    0.39
     Polyester
    0.39
     inability
    0.39
     निधन
    0.38
     상황
    0.38
    Activations Density 0.001%

    No Known Activations