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. 5068
    Prev
    Next
    INDEX
    Explanations

    love with

    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
    ires
    0.49
    دا
    0.45
    োর্স
    0.44
    itably
    0.44
    Her
    0.43
     Qxc
    0.41
    azone
    0.40
    -【
    0.40
     Her
    0.40
    plated
    0.40
    POSITIVE LOGITS
     програми
    0.50
     canzone
    0.46
    м
    0.46
     зрения
    0.46
     أعلى
    0.46
     chứng
    0.45
     dikdört
    0.44
     ون
    0.44
     вдох
    0.44
     charisma
    0.44
    Activations Density 0.000%

    No Known Activations