© 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. 17803
    Prev
    Next
    INDEX
    Explanations

    viewport width setting

    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
    <0xD2>
    0.45
    נ
    0.45
    ultur
    0.45
     ფ
    0.44
    ง
    0.44
    🕸
    0.43
    acula
    0.43
    💾
    0.43
    リ
    0.42
    Ҡ
    0.42
    POSITIVE LOGITS
     denaturation
    0.45
     prohibiting
    0.41
     Kog
    0.41
     pemeriksaan
    0.41
     viewport
    0.40
     vaut
    0.40
     salicylate
    0.40
     cốc
    0.40
     basking
    0.40
    viewport
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.