© 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-16K
    7. 12863
    Prev
    Next
    INDEX
    Explanations

    category, transaction, his, her

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

    multilingual text fragments

    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_16k_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
    ཌ
    0.49
     ప
    0.41
    པ
    0.41
    幂
    0.40
     sebagainya
    0.38
    པ་
    0.38
     framebuffer
    0.38
    ୱ
    0.37
    Ꮘ
    0.37
    intaan
    0.37
    POSITIVE LOGITS
     Instead
    0.41
    Miller
    0.40
     nincs
    0.39
     Selv
    0.38
    Sim
    0.37
     Miller
    0.36
     எந்த
    0.36
    Instead
    0.35
     никаких
    0.35
    tidak
    0.35
    Activations Density 0.329%

    No Known Activations