© 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. 174101
    Prev
    Next
    INDEX
    Explanations

    silk, silicon, lactic

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

    offering help and guidance

    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
    웰
    0.48
    ці
    0.47
    نيك
    0.46
    ד
    0.46
     Ці
    0.46
    ্দ
    0.46
    رین
    0.44
    መት
    0.43
    n
    0.43
    ット
    0.43
    POSITIVE LOGITS
     Silk
    0.50
     silk
    0.49
     lactic
    0.48
     silicon
    0.47
     silenced
    0.47
     ubiqu
    0.46
     quark
    0.46
     transfected
    0.45
     Darth
    0.45
     ling
    0.44
    Activations Density 0.003%

    No Known Activations