© 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. 249576
    Prev
    Next
    INDEX
    Explanations

    . the. the. purchase

    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
    光的
    0.49
    月末
    0.48
     Flamingo
    0.47
     সন্ধ্যার
    0.46
    rifft
    0.45
     florals
    0.45
     mangroves
    0.45
    墮
    0.45
     કરવા
    0.44
     feest
    0.44
    POSITIVE LOGITS
    é
    0.53
    මුත්
    0.51
    ind
    0.49
    até
    0.45
    ček
    0.44
    ému
    0.44
    িয়ার
    0.44
    asang
    0.43
    ad
    0.43
    ội
    0.43
    Activations Density 0.001%

    No Known Activations