Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 35315
    Prev
    Next
    INDEX
    Explanations

    AI models, technology, and personal life

    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
    e
    0.55
    í
    0.55
    in
    0.53
    led
    0.49
    integer
    0.49
    d
    0.49
    ная
    0.46
    ene
    0.46
    text
    0.45
    vay
    0.45
    POSITIVE LOGITS
     modèles
    0.60
     struggles
    0.52
     पक्षों
    0.51
     bouts
    0.51
    ﺮ
    0.51
     acteurs
    0.50
     пациентов
    0.50
     අප
    0.50
    বিস্ত
    0.49
     cheerfully
    0.49
    Activations Density 0.001%

    No Known Activations