© 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-262K
    7. 119425
    Prev
    Next
    INDEX
    Explanations

    TfidfVectorizer

    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_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
    ക്ക്‌
    0.43
    ઓને
    0.40
     bag
    0.39
    فة
    0.39
    ylsulfanyl
    0.38
    蓬
    0.37
     фе
    0.37
     प्रार्थना
    0.37
    ۊ
    0.36
    approval
    0.36
    POSITIVE LOGITS
    Transformer
    0.50
    Matrix
    0.48
    idf
    0.47
     Transformer
    0.46
    Transform
    0.45
    Rank
    0.45
     matrices
    0.45
     transformer
    0.45
    Weight
    0.45
    Scores
    0.44
    Activations Density 0.004%

    No Known Activations