© 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. 115190
    Prev
    Next
    INDEX
    Explanations

    athletes always, foreign exchange, tree trunk

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

    background and skills

    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
    すべての
    0.49
    全ての
    0.49
    可能です
    0.45
    <0xB3>
    0.45
    、
    0.45
    ㄩ
    0.45
    issimus
    0.44
    7
    0.44
    無法
    0.44
    符合
    0.44
    POSITIVE LOGITS
     bertanya
    0.47
     Oktoberfest
    0.45
     Ikea
    0.45
     éché
    0.45
     largement
    0.44
     ciddi
    0.43
     propriet
    0.42
     वर्ग
    0.42
     Architektur
    0.42
     önemli
    0.41
    Activations Density 0.002%

    No Known Activations