© 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. 60858
    Prev
    Next
    INDEX
    Explanations

    future, specific, categories

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

    performance and accuracy limits

    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
    now
    0.50
    op
    0.49
    wallpaper
    0.47
    href
    0.47
    ứng
    0.47
    since
    0.46
    tong
    0.46
    p
    0.46
    ka
    0.45
    thumb
    0.45
    POSITIVE LOGITS
     思い
    0.53
     racional
    0.52
     hará
    0.52
     résoudre
    0.50
     faça
    0.50
     especializados
    0.49
     quieren
    0.49
    你会
    0.49
     crée
    0.48
     കരുത
    0.48
    Activations Density 0.000%

    No Known Activations