© 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. 134699
    Prev
    Next
    INDEX
    Explanations

    discounted tires

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

    LSTM, RNN, planets

    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
    us
    0.53
    ag
    0.52
    are
    0.52
    aw
    0.52
    chrome
    0.52
    aS
    0.51
    ৭
    0.51
     Chrome
    0.50
    ﻄ
    0.50
    енера
    0.50
    POSITIVE LOGITS
     крепо
    0.46
     постепенно
    0.46
    基地
    0.45
    FORMAN
    0.45
     मेगा
    0.44
     JMJD
    0.44
     postulates
    0.44
     масса
    0.43
     которых
    0.43
     заро
    0.43
    Activations Density 0.000%

    No Known Activations