© 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. 137833
    Prev
    Next
    INDEX
    Explanations

    drawers measured parallel is is

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

    you've mentioned

    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
     orde
    0.55
    vend
    0.49
    별
    0.49
    ორ
    0.49
    z
    0.48
    팝
    0.45
     چک
    0.44
    ის
    0.44
     recue
    0.44
    옥
    0.44
    POSITIVE LOGITS
     Coach
    0.48
    Icon
    0.48
     Squad
    0.46
     шка
    0.46
    <0xA3>
    0.46
     LRC
    0.46
    Coach
    0.45
     Figs
    0.44
     Conditioning
    0.44
     Transforming
    0.44
    Activations Density 0.000%

    No Known Activations