© 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. 78347
    Prev
    Next
    INDEX
    Explanations

    vinyl fence

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

    font rendering

    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
     nhưng
    0.51
     ۳
    0.50
     месяца
    0.48
     ۲
    0.48
     ২০
    0.47
     অর্ধেক
    0.46
     fermeture
    0.46
     yaklaşık
    0.46
     لیکن
    0.46
     wynik
    0.46
    POSITIVE LOGITS
    adz
    0.47
    adds
    0.46
    <0xE9>
    0.46
    Œ
    0.45
    ADE
    0.44
     proposer
    0.43
    create
    0.43
    oids
    0.42
    strate
    0.42
    át
    0.42
    Activations Density 0.001%

    No Known Activations