© 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. 850
    Prev
    Next
    INDEX
    Explanations

    query operators

    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
    αι
    0.58
    规划
    0.58
    اری
    0.56
    Derivative
    0.56
    アナログ
    0.56
    Riley
    0.55
    ﻨ
    0.55
    ري
    0.53
    ﻜ
    0.53
    エリ
    0.52
    POSITIVE LOGITS
     in
    0.80
     d
    0.69
    ed
    0.66
     ins
    0.65
     for
    0.62
     https
    0.61
     clang
    0.58
     as
    0.57
     http
    0.57
     ed
    0.56
    Activations Density 0.000%

    No Known Activations