© 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. 150742
    Prev
    Next
    INDEX
    Explanations

    store POS system

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

    antelope canyon

    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
     Company
    0.50
     어떤
    0.48
    complete
    0.48
     सतत
    0.47
     을
    0.47
     上
    0.46
     वैकल्पिक
    0.46
    ’;
    0.46
     Perkenalkan
    0.46
     socialize
    0.46
    POSITIVE LOGITS
    中美
    0.52
    CLASSES
    0.51
    Coffee
    0.46
    ફેદ
    0.46
     videa
    0.45
    mixed
    0.45
     maestra
    0.45
    Trung
    0.44
    Mixed
    0.44
    يروس
    0.43
    Activations Density 0.000%

    No Known Activations