© 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. 18197
    Prev
    Next
    INDEX
    Explanations

    transactional or descriptive openers

    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
    fadeIn
    0.48
    του
    0.45
    τιο
    0.45
     måtte
    0.44
    тері
    0.44
    անում
    0.43
    㝡
    0.43
    աս
    0.43
     riguardo
    0.43
    ższ
    0.42
    POSITIVE LOGITS
    ive
    0.44
    s
    0.42
    ead
    0.42
    ك
    0.42
     partly
    0.41
     zag
    0.41
     oasis
    0.40
    nYou
    0.40
     communicate
    0.40
     indemn
    0.40
    Activations Density 0.002%

    No Known Activations