© 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. 50964
    Prev
    Next
    INDEX
    Explanations

    FUSION, narrator, propensity model

    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
     Ка
    0.51
     Доб
    0.50
     Т
    0.50
     специали
    0.50
     إ
    0.48
     М
    0.46
     unten
    0.46
     Лю
    0.46
     Слу
    0.46
    靈
    0.46
    POSITIVE LOGITS
    phony
    0.61
    Infl
    0.52
    Tip
    0.48
    Is
    0.47
    Free
    0.47
    Pre
    0.46
    erView
    0.46
    South
    0.45
    Uk
    0.44
    aneers
    0.44
    Activations Density 0.001%

    No Known Activations