© 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. 13513
    Prev
    Next
    INDEX
    Explanations

    body parts and biological systems

    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
     yatırım
    0.57
    ໂດ
    0.54
    Oréal
    0.54
     బ్యాం
    0.53
    赌场
    0.52
    栱
    0.51
    atasaray
    0.50
    ယူ
    0.50
    Flagge
    0.49
     казіно
    0.49
    POSITIVE LOGITS
     __________
    0.59
     ________
    0.57
     som
    0.56
     ____
    0.55
     scanty
    0.54
     =
    0.53
     D
    0.52
     events
    0.52
     modifications
    0.52
     ____________
    0.50
    Activations Density 0.020%

    No Known Activations