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. 40-GEMMASCOPE-2-RES-262K
    4. 14885
    Prev
    Next
    INDEX
    Explanations

    tech and AI links

    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
     usa
    0.45
     Usa
    0.42
     wiring
    0.40
     ám
    0.38
     magasin
    0.38
     electricidad
    0.38
     jedan
    0.37
    Ⅰ
    0.37
     wrześ
    0.37
     maneiras
    0.37
    POSITIVE LOGITS
    🤖
    0.50
    /@
    0.48
     Notion
    0.45
    GPT
    0.43
     Google
    0.42
    /[
    0.42
     @
    0.41
    Google
    0.41
    /%
    0.41
     OpenAI
    0.41
    Activations Density 0.003%

    No Known Activations