© 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. 138684
    Prev
    Next
    INDEX
    Explanations

    deploy, approach, hunting, decided, Wednesday, improved

    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
     balo
    0.52
     intoxicated
    0.46
     maliciously
    0.45
     rakh
    0.45
     g
    0.44
     hippocampal
    0.44
     г
    0.43
     helium
    0.43
     নুর
    0.43
     Shetty
    0.43
    POSITIVE LOGITS
    क्का
    0.47
     Finds
    0.46
    accur
    0.44
    ptic
    0.44
    Foo
    0.44
    သုံးပြု
    0.44
    ptr
    0.42
     Goals
    0.41
    trick
    0.41
    끔
    0.41
    Activations Density 0.003%

    No Known Activations