© 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. 40-GEMMASCOPE-2-RES-262K
    7. 223510
    Prev
    Next
    INDEX
    Explanations

    seeing or appointments

    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_40_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
    பிர
    0.42
    ày
    0.41
    ảng
    0.39
     médicale
    0.39
    辏
    0.39
    Medical
    0.39
    stethoscope
    0.38
     appointment
    0.38
    ELD
    0.37
     прогу
    0.37
    POSITIVE LOGITS
     seeing
    1.49
    见
    1.45
     see
    1.36
    見
    1.34
     sees
    1.30
     Seeing
    1.25
     thấy
    1.24
    seeing
    1.23
     saw
    1.21
     SEE
    1.20
    Activations Density 0.010%

    No Known Activations