© 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. 154554
    Prev
    Next
    INDEX
    Explanations

    increasing expansion, your requirements, for discounted

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

    questions and concepts

    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
    allowSlide
    0.53
     LOG
    0.51
    ಿವೆ
    0.51
     TouchUtils
    0.50
     MIUI
    0.48
     CASH
    0.47
    ේශ
    0.47
    ۷
    0.47
    ໃຈ
    0.46
     Indonesian
    0.46
    POSITIVE LOGITS
    her
    0.50
    0
    0.49
    pars
    0.49
    ermo
    0.47
    ét
    0.47
    -
    0.46
    boden
    0.45
    erm
    0.45
    멘
    0.45
    헛
    0.44
    Activations Density 0.001%

    No Known Activations