© 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. 35512
    Prev
    Next
    INDEX
    Explanations

    specific conditions with listed details

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

    chess notation rnbqkbnr

    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
    িলম্বে
    0.48
    脱
    0.48
    Server
    0.47
    侍
    0.45
    ن
    0.44
    停车
    0.44
    于
    0.44
    もちろん
    0.43
     leite
    0.43
    server
    0.43
    POSITIVE LOGITS
     треть
    0.55
     появилась
    0.52
    adav
    0.51
    apatt
    0.51
     -
    0.50
     または
    0.50
    ického
    0.50
    )।
    0.50
     或者
    0.50
     -\
    0.49
    Activations Density 0.000%

    No Known Activations