© 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. 162288
    Prev
    Next
    INDEX
    Explanations

    commercial interests

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

    code structure and specific terms

    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
    وبی
    0.55
    𓍊
    0.54
     लगभग
    0.52
    ोब
    0.52
    🥉
    0.52
    畄
    0.51
     হওয়
    0.50
     Bromley
    0.49
     கிட்டத்தட்ட
    0.49
     تقریباً
    0.48
    POSITIVE LOGITS
     output
    0.51
     var
    0.50
    <start_of_image>
    0.50
        
    0.49
     business
    0.48
     pip
    0.48
    <0x80>
    0.48
     port
    0.48
     speed
    0.47
     SH
    0.46
    Activations Density 0.000%

    No Known Activations