© 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. 245697
    Prev
    Next
    INDEX
    Explanations

    terms and deadlines

    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
    瑆
    0.54
     วิ
    0.46
     Wonderful
    0.45
    ম
    0.45
    咣
    0.45
     कर्व
    0.44
    玩意
    0.44
    อร์
    0.43
    我认为
    0.43
     Վ
    0.43
    POSITIVE LOGITS
     voluminous
    0.48
    TRANSPORT
    0.48
     TRANSPORT
    0.46
     транспо
    0.46
    TRAVEL
    0.44
     extras
    0.44
     oversized
    0.43
     речо
    0.43
     adecuados
    0.43
     sublattice
    0.43
    Activations Density 0.001%

    No Known Activations