© 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. 135946
    Prev
    Next
    INDEX
    Explanations

    has changed, evolution of, will surely

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

    introducing sections or topics

    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
    u
    0.48
    lina
    0.46
    olini
    0.46
    omos
    0.45
    uine
    0.44
    olive
    0.44
    orus
    0.44
    idus
    0.44
     समास
    0.44
    ucaly
    0.43
    POSITIVE LOGITS
    ของ
    0.55
     của
    0.53
     okre
    0.45
    ใหญ
    0.45
    踉
    0.45
     przyst
    0.44
     بیاکتنې
    0.44
     জোগ
    0.43
     undergoing
    0.43
    وق
    0.43
    Activations Density 0.000%

    No Known Activations