Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 43662
    Prev
    Next
    INDEX
    Explanations

    approximations

    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
    اد
    0.47
    ADEL
    0.46
     alkaloids
    0.44
     annihilated
    0.43
    دا
    0.42
     espèces
    0.42
    S
    0.42
    ارو
    0.42
    Zb
    0.42
    έρ
    0.41
    POSITIVE LOGITS
     copi
    0.41
     હજાર
    0.40
     ឬ
    0.40
    ֙
    0.39
     sorprend
    0.39
     посредством
    0.38
    뷰
    0.38
     touching
    0.38
     stimulating
    0.38
     অবদান
    0.38
    Activations Density 0.000%

    No Known Activations