© 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-65K
    7. 40379
    Prev
    Next
    INDEX
    Explanations

    full name

    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_65k_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
    ین
    0.53
    ر
    0.51
    бота
    0.46
     кількість
    0.46
     quarant
    0.44
    ヴァ
    0.43
    poses
    0.43
     tally
    0.43
    ય
    0.42
    at
    0.42
    POSITIVE LOGITS
    Ûn
    0.50
     Schreib
    0.50
     walkway
    0.49
     dará
    0.47
     Biography
    0.46
     sarà
    0.46
     الترم
    0.45
    Wedgwood
    0.45
     Biografie
    0.45
     Objekt
    0.45
    Activations Density 0.002%

    No Known Activations