© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 13107
    Prev
    Next
    INDEX
    Explanations

    from a library

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

    require, progress, Rae, Glenlivet, Lermontov

    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_16k_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
    uuuu
    0.49
    ().
    0.45
    ands
    0.45
    ()
    0.44
    (
    0.44
    ał
    0.44
    ela
    0.43
     emoc
    0.43
    rinos
    0.43
    allowed
    0.42
    POSITIVE LOGITS
    }\|_{
    0.54
     scriptlevel
    0.48
     ಮಾಡುವ
    0.47
     ಸಾವಿರ
    0.47
     దూర
    0.47
     CONCLUSIONS
    0.47
    విద్య
    0.47
     отправ
    0.46
     нормы
    0.46
    <unused25>
    0.46
    Activations Density 0.001%

    No Known Activations