© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 228919
    Prev
    Next
    INDEX
    Explanations

    plan/best practices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     خودم
    0.52
     don
    0.50
     pédicule
    0.50
    𝚙
    0.50
    ून्य
    0.47
     главного
    0.47
     개의
    0.47
    スペース
    0.46
     进行
    0.46
     ట్రా
    0.46
    POSITIVE LOGITS
    :
    0.50
     lives
    0.46
     Lives
    0.46
    二年
    0.43
     yearbook
    0.43
     Ocean
    0.42
    '
    0.42
     yılı
    0.42
    tions
    0.42
     SOL
    0.40
    Activations Density 0.000%

    No Known Activations