© 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. 166118
    Prev
    Next
    INDEX
    Explanations

    most industries

    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
    орк
    0.44
     recipient
    0.43
     grab
    0.41
    grab
    0.39
     seleccionar
    0.39
    뽑
    0.37
     personnaliser
    0.37
     publie
    0.36
    ütü
    0.36
    Connor
    0.36
    POSITIVE LOGITS
    éről
    0.42
     многое
    0.41
     мебель
    0.40
     चीजों
    0.38
     الجز
    0.36
     ቤ
    0.35
     изделий
    0.35
     dichloromethane
    0.35
    vartheta
    0.35
     inval
    0.35
    Activations Density 0.000%

    No Known Activations