© 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. 13894
    Prev
    Next
    INDEX
    Explanations

    research findings

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

    academic research

    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
    ྥ
    0.77
    rik
    0.73
    ண்ட்
    0.71
    心
    0.71
    手
    0.68
    美女
    0.66
    να
    0.65
    ր
    0.65
    地方
    0.64
     कॉल्ड
    0.64
    POSITIVE LOGITS
     araşt
    0.99
     research
    0.97
     in
    0.93
     RESEARCH
    0.92
    RESEARCH
    0.90
     Research
    0.89
    research
    0.89
    Research
    0.88
     istraž
    0.86
    Researchers
    0.85
    Activations Density 0.057%

    No Known Activations