© 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-262K
    7. 84690
    Prev
    Next
    INDEX
    Explanations

    Chrétien de Troyes, Impressionism, confusion

    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
    ี
    0.48
    in
    0.44
    :
    0.44
    지
    0.44
    MD
    0.43
    ARD
    0.43
     humour
    0.43
     struggling
    0.42
    ates
    0.42
     trud
    0.42
    POSITIVE LOGITS
     kanamycin
    0.58
     yellowish
    0.52
    াইয়৷
    0.52
     Violation
    0.50
     пайда
    0.50
     hồng
    0.49
     samano
    0.49
     några
    0.48
    鉆
    0.48
    netHex
    0.48
    Activations Density 0.005%

    No Known Activations