© 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. 40-GEMMASCOPE-2-RES-65K
    7. 780
    Prev
    Next
    INDEX
    Explanations

    adjusting instructions or details

    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_40_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
     videos
    0.47
    all
    0.46
    videos
    0.45
     answers
    0.43
    cellent
    0.43
    answers
    0.42
    :</
    0.42
    enz
    0.42
     replies
    0.42
     Answers
    0.41
    POSITIVE LOGITS
    卡
    0.38
     notas
    0.38
     প্রকৃতির
    0.36
     impeding
    0.36
     σκ
    0.35
     oppressive
    0.35
     acorde
    0.34
    ्रीट
    0.34
     foco
    0.34
    Fighting
    0.34
    Activations Density 0.001%

    No Known Activations