© 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. 4134
    Prev
    Next
    INDEX
    Explanations

    let's break down

    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
     Mijn
    0.43
    риал
    0.41
    สนุก
    0.40
    屾
    0.40
    গঞ্জে
    0.40
    splitLength
    0.40
    varsigma
    0.39
    轭
    0.39
     فونبټ
    0.39
     ዘዴ
    0.39
    POSITIVE LOGITS
    ayer
    0.44
    profile
    0.43
     heavy
    0.43
     &
    0.42
     di
    0.42
     in
    0.41
     is
    0.41
     function
    0.41
     exhibits
    0.40
     something
    0.40
    Activations Density 0.001%

    No Known Activations