© 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. 194532
    Prev
    Next
    INDEX
    Explanations

    mining counters style

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

    incumbent president

    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
    atient
    0.46
     определяется
    0.45
    COMPONENT
    0.45
    Fit
    0.44
    凵
    0.44
    取决于
    0.44
    SEQUENCE
    0.43
     শিক্ষার্থীরা
    0.43
    ˶
    0.42
    运动员
    0.42
    POSITIVE LOGITS
     slogan
    0.50
     slogans
    0.50
     تصاویر
    0.46
     grö
    0.44
     homen
    0.44
     하고
    0.43
     dihasil
    0.43
     عکس
    0.43
     hefyd
    0.43
     हंस
    0.42
    Activations Density 0.001%

    No Known Activations