© 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. 86555
    Prev
    Next
    INDEX
    Explanations

    released by2x more absorbentglue is strongkeeps us

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

    asking questions

    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
    이지만
    0.51
     be
    0.50
     trochu
    0.49
     buen
    0.48
     trebalo
    0.48
     realize
    0.47
    认
    0.47
     soma
    0.47
     realiza
    0.46
     pied
    0.46
    POSITIVE LOGITS
    curl
    0.46
    '(
    0.46
    xAxis
    0.45
    :'',
    0.45
    :,
    0.45
     ウ
    0.45
    fadeOut
    0.45
    Wallpaper
    0.45
    äger
    0.45
    lož
    0.44
    Activations Density 0.000%

    No Known Activations