© 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. 81038
    Prev
    Next
    INDEX
    Explanations

    alternative or substitute

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

    security, devices, and calculations

    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
     통해서
    0.50
    Instruct
    0.46
    টিশ
    0.44
    蒖
    0.43
     структур
    0.41
     போல
    0.41
     Deshalb
    0.41
    贴
    0.40
    乑
    0.40
     সুষ্ঠ
    0.40
    POSITIVE LOGITS
    ०
    0.59
     mua
    0.48
    *
    0.47
    ке
    0.46
    à
    0.46
     kT
    0.45
    <0xE0>
    0.45
    $
    0.45
    ;
    0.44
     roaming
    0.44
    Activations Density 0.003%

    No Known Activations