© 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. 4418
    Prev
    Next
    INDEX
    Explanations

    proprietary hardware terms

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

    features and specifications

    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
     遊ん
    0.65
    社會
    0.64
    㵴
    0.61
    🕜
    0.59
    PAssignment
    0.59
    ᅴ
    0.58
     ಆರೋಗ್ಯ
    0.56
    𐰣
    0.56
    CONCLUSION
    0.55
    👱
    0.55
    POSITIVE LOGITS
     patented
    0.79
     OEM
    0.75
     proprietary
    0.75
     silicone
    0.72
     bushings
    0.71
     warranty
    0.70
     velcro
    0.70
     clamps
    0.70
     microfiber
    0.69
     amperage
    0.69
    Activations Density 0.092%

    No Known Activations