© 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. 111643
    Prev
    Next
    INDEX
    Explanations

    skin, biology, inclusive

    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
     (
    0.49
     Odin
    0.40
    lend
    0.38
     renov
    0.38
    원을
    0.38
     =-
    0.38
     অপরা
    0.38
     hort
    0.37
     Finnish
    0.37
     upaya
    0.37
    POSITIVE LOGITS
    তরাং
    0.54
    含
    0.52
     marchandises
    0.48
    造成
    0.48
    ತ್ತು
    0.46
    គ្មាន
    0.44
    řit
    0.44
    ዒ
    0.44
    ステージ
    0.44
    ڎ
    0.44
    Activations Density 0.001%

    No Known Activations