© 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-65K
    7. 36217
    Prev
    Next
    INDEX
    Explanations

    recallcars, tap, balls, water

    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_65k_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
    িকপ্ট
    0.49
    做一个
    0.47
    らない
    0.46
    質の
    0.45
     symbiotic
    0.44
     nostrum
    0.44
    щик
    0.43
    」
    0.43
    مانی
    0.43
     subconscious
    0.43
    POSITIVE LOGITS
    ADE
    0.46
     הג
    0.41
     វា
    0.41
     أع
    0.41
    abel
    0.40
     ADE
    0.40
    Ma
    0.40
     درجة
    0.39
     확
    0.39
    Quelle
    0.39
    Activations Density 0.010%

    No Known Activations