© 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. 101054
    Prev
    Next
    INDEX
    Explanations

    package debug

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

    diverse list of words

    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
    henti
    0.50
    favorite
    0.50
    留下
    0.50
    recipe
    0.48
    industry
    0.48
    лимпий
    0.47
    2
    0.47
    remark
    0.46
    鴿
    0.46
    aw
    0.45
    POSITIVE LOGITS
     améli
    0.61
     números
    0.48
     Dés
    0.47
     auraient
    0.47
     Claus
    0.47
     росій
    0.46
     Чар
    0.46
     selon
    0.46
     اکثر
    0.46
     endere
    0.46
    Activations Density 0.000%

    No Known Activations