© 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. 195829
    Prev
    Next
    INDEX
    Explanations

    non-english characters

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

    Algorithm, job, species, start

    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
     convenc
    0.51
    e
    0.46
     mercado
    0.45
    zoek
    0.44
    워크
    0.44
     pored
    0.44
    ชื่อ
    0.43
     Armani
    0.43
    жного
    0.42
     pitches
    0.42
    POSITIVE LOGITS
     DISABLE
    0.48
    教學
    0.47
     VERY
    0.47
     cancelButton
    0.46
    १
    0.46
    會在
    0.46
     スタッドレス
    0.46
     cmake
    0.46
    年生
    0.45
     ακ
    0.43
    Activations Density 0.000%

    No Known Activations