© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 3106
    Prev
    Next
    INDEX
    Explanations

    associates business and technical terms

    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
    *
    0.51
    *,
    0.48
     النهايات
    0.47
    مرين
    0.46
    October
    0.46
    ी
    0.46
    ระ
    0.45
    ட
    0.45
    ק
    0.44
    देश
    0.44
    POSITIVE LOGITS
    utam
    0.41
     broader
    0.41
     Ralf
    0.41
    schap
    0.40
    stahl
    0.40
     his
    0.39
     Zion
    0.39
     Zijn
    0.39
    াহিদ
    0.39
     retry
    0.39
    Activations Density 0.015%

    No Known Activations