© 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. 135644
    Prev
    Next
    INDEX
    Explanations

    state of agreement

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

    child lexicon and physical therapy

    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
     in
    0.49
    t
    0.47
    orden
    0.45
    techn
    0.44
    fra
    0.43
     cogn
    0.42
    v
    0.42
    pr
    0.42
    co
    0.41
    money
    0.41
    POSITIVE LOGITS
    らを
    0.54
    ણો
    0.54
     交換
    0.54
    انوں
    0.52
     refuted
    0.52
     包括
    0.51
     любить
    0.50
    ಗಳು
    0.50
    етесь
    0.50
     刺繍
    0.50
    Activations Density 0.001%

    No Known Activations