© 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. 231591
    Prev
    Next
    INDEX
    Explanations

    menu bar, sideboard, counsel for

    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
     молеку
    0.55
     очи
    0.53
     бой
    0.53
     бор
    0.52
     вещества
    0.52
    િયા
    0.51
     Blockchain
    0.51
     %}
    0.50
     Achievements
    0.49
     bijection
    0.49
    POSITIVE LOGITS
    ۳
    0.45
    ৩৮
    0.42
    dem
    0.41
    দ্দিক
    0.40
    ৩
    0.40
    Is
    0.39
    ಟೆ
    0.39
    थिक
    0.39
    )',
    0.38
    vär
    0.38
    Activations Density 0.001%

    No Known Activations