© 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. 227079
    Prev
    Next
    INDEX
    Explanations

    either/or or meets/science

    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
    िन्न
    0.52
    HISTORY
    0.51
    ഫ
    0.50
    '
    0.50
    ിവ
    0.48
     bureaus
    0.48
     acred
    0.48
    ection
    0.48
    িন্ন
    0.48
    Historia
    0.47
    POSITIVE LOGITS
     Tecnología
    0.54
     آزمایش
    0.46
     红
    0.46
     умови
    0.45
    ⑨
    0.45
    溅
    0.45
     Muir
    0.42
     Kristin
    0.41
     倍
    0.41
    ستان
    0.41
    Activations Density 0.000%

    No Known Activations