© 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. 48921
    Prev
    Next
    INDEX
    Explanations

    patterns or examples

    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
     pursuance
    0.50
    ามารถ
    0.50
    汜
    0.49
     maaaring
    0.48
     riconosci
    0.48
     sebagaimana
    0.48
     সংরক্ষণ
    0.47
     নিঃসন্দেহে
    0.46
    %';
    0.46
     میتوان
    0.46
    POSITIVE LOGITS
    username
    0.49
     Twitter
    0.47
    Twitter
    0.47
    Facebook
    0.46
    Email
    0.45
    controller
    0.45
    Ow
    0.45
     a
    0.44
     microphone
    0.44
    internet
    0.44
    Activations Density 0.006%

    No Known Activations