© 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. 196386
    Prev
    Next
    INDEX
    Explanations

    language and typists

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

    questions starting with "Do you" or "Know"

    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
    <h2>
    0.49
    नामेंट
    0.48
    uldades
    0.48
     अन्दर
    0.47
    만에
    0.47
    ଅ
    0.46
    <h5>
    0.46
     )\
    0.46
    <h4>
    0.45
    만의
    0.44
    POSITIVE LOGITS
     prefeito
    0.50
    hita
    0.48
     filepath
    0.48
    དང་
    0.46
    第一個
    0.46
    قى
    0.45
     عليك
    0.45
     arbre
    0.45
     გამოყენ
    0.45
    各式
    0.45
    Activations Density 0.001%

    No Known Activations