© 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. 16-GEMMASCOPE-2-RES-262K
    7. 85906
    Prev
    Next
    INDEX
    Explanations

    frost and timing

    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_16_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
     de
    0.62
     hop
    0.57
     Blaze
    0.55
     hopping
    0.55
     *
    0.54
     dite
    0.53
     dit
    0.52
     deze
    0.52
     ramb
    0.52
     tic
    0.52
    POSITIVE LOGITS
    드
    0.59
    Д
    0.59
    ม
    0.57
    ز
    0.56
    اص
    0.54
    浙江
    0.54
    Р
    0.53
    ขาย
    0.53
    ک
    0.53
    ك
    0.53
    Activations Density 0.000%

    No Known Activations