© 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. 4423
    Prev
    Next
    INDEX
    Explanations

    accessories for hair

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

    DIY accessories

    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
     політи
    0.53
     биографи
    0.53
    变革
    0.52
     législ
    0.51
     ентите
    0.51
    <unused88>
    0.50
     угро
    0.50
     контек
    0.49
    罹
    0.49
    嬗
    0.49
    POSITIVE LOGITS
     exquisite
    0.60
     waterproof
    0.57
     WIFI
    0.55
    it
    0.55
     ，
    0.55
     it
    0.54
     DIY
    0.54
     Xiao
    0.54
    ，
    0.54
     ：
    0.54
    Activations Density 0.106%

    No Known Activations