© 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. 44328
    Prev
    Next
    INDEX
    Explanations

    welcome to

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

    custom templates

    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
    DIO
    0.45
    SIGNED
    0.44
     o
    0.44
    physical
    0.43
    1
    0.43
    5
    0.43
    ee
    0.43
     Sait
    0.43
    ohms
    0.43
    lambda
    0.43
    POSITIVE LOGITS
    動画
    0.56
     動画
    0.51
    mandu
    0.50
     Michelangelo
    0.50
    鮮
    0.48
    每个人
    0.47
     rassembl
    0.47
    izia
    0.47
    መል
    0.47
    主角
    0.46
    Activations Density 0.000%

    No Known Activations