© 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. 113243
    Prev
    Next
    INDEX
    Explanations

    regulations and disposal

    np_acts-logits-general · gemini-2.5-flash-lite

    submission and abuse

    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
    ஸ்த
    0.50
    Ⴖ
    0.50
    ाइल
    0.47
    ilege
    0.46
     ライン
    0.46
    lenme
    0.46
    selfobj
    0.46
    ಢ
    0.46
    ართველოს
    0.45
    ೮
    0.45
    POSITIVE LOGITS
     processor
    0.52
     processing
    0.48
     Processor
    0.47
     repository
    0.46
     xử
    0.45
     casino
    0.44
     checker
    0.44
     Processing
    0.44
     shopper
    0.44
     supermarket
    0.42
    Activations Density 0.000%

    No Known Activations