© 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. 68849
    Prev
    Next
    INDEX
    Explanations

    our finest/best/ideal pictures

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

    requesting content and information

    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
     visites
    0.50
     функция
    0.50
    ...");
    0.49
    !!!");
    0.48
     gouver
    0.48
     abhor
    0.48
     сигнала
    0.47
     περισ
    0.46
    更为
    0.46
    北
    0.46
    POSITIVE LOGITS
     flat
    0.48
     eosin
    0.46
     James
    0.45
     are
    0.45
     mandate
    0.44
     aeration
    0.44
     ff
    0.44
     final
    0.43
     mix
    0.42
     cure
    0.42
    Activations Density 0.001%

    No Known Activations