© 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. 87780
    Prev
    Next
    INDEX
    Explanations

    if you

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

    why and how

    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
    Raven
    0.51
    iciona
    0.49
    ार्थी
    0.49
     교회
    0.48
    핼
    0.48
     음식
    0.47
    ार्म
    0.47
     결혼
    0.46
     먹
    0.46
     वरना
    0.45
    POSITIVE LOGITS
    <0x80>
    0.52
    >(){
    0.51
    ет
    0.46
    ATORS
    0.46
    >();
    0.46
     ALLEN
    0.45
     danni
    0.45
    ים
    0.44
    то
    0.44
     Fass
    0.43
    Activations Density 0.002%

    No Known Activations