© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 30983
    Prev
    Next
    INDEX
    Explanations

    color, witty, printing, product, arbitrator

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

    foreign and specific 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
     Life
    0.49
    ä
    0.48
    re
    0.47
    rami
    0.47
    ט
    0.46
    arium
    0.45
    etera
    0.44
    ش
    0.44
     st
    0.43
     Eur
    0.43
    POSITIVE LOGITS
     ileri
    0.53
    CHREIB
    0.51
    長く
    0.51
    BRAND
    0.51
    AppDelegate
    0.48
     doubtless
    0.48
    при
    0.48
    Dij
    0.48
     hôtel
    0.48
    uğ
    0.48
    Activations Density 0.000%

    No Known Activations