© 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. 109558
    Prev
    Next
    INDEX
    Explanations

    body elements and related substances

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

    modelmodel size

    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
    وک
    0.46
    žio
    0.45
    ್ಯ
    0.45
     얼마
    0.45
     oleks
    0.45
    ی
    0.44
    ༢
    0.44
     ilegal
    0.43
    ลา
    0.43
    ס
    0.43
    POSITIVE LOGITS
     HTMLSc
    0.44
     পশ্চিমবঙ্গের
    0.43
     grassy
    0.43
    
    0.43
     香港
    0.42
     জাতিকে
    0.42
    autoconfigure
    0.41
     अभिकथन
    0.41
     લક્ષ
    0.41
     problemy
    0.41
    Activations Density 0.000%

    No Known Activations