© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 113386
    Prev
    Next
    INDEX
    Explanations

    timing, calendar, girl, AI

    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
    び
    0.45
    CAN
    0.42
    is
    0.41
     ecuaciones
    0.41
     retour
    0.40
     bitten
    0.40
    iefert
    0.39
    UN
    0.39
    DIM
    0.39
    ේ
    0.39
    POSITIVE LOGITS
     Thailand
    0.52
     Tales
    0.50
     Avon
    0.49
     Council
    0.49
     sporting
    0.49
     Village
    0.48
     Watt
    0.47
     หาก
    0.47
     Taal
    0.47
     Watts
    0.47
    Activations Density 0.006%

    No Known Activations