© 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. 240988
    Prev
    Next
    INDEX
    Explanations

    posted on or

    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
    Aside
    0.51
     elegan
    0.48
     লা
    0.46
     dễ
    0.45
    )];
    0.45
     নিখ
    0.44
    bindingFields
    0.44
    ષ્ઠ
    0.44
     plastica
    0.44
     ব্যাক
    0.43
    POSITIVE LOGITS
     Directors
    0.48
    적으로
    0.47
     levies
    0.47
    МУ
    0.46
    로부터
    0.44
    합
    0.44
     Maddox
    0.43
    бра
    0.41
     감독
    0.41
    рует
    0.40
    Activations Density 0.000%

    No Known Activations