© 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. 85001
    Prev
    Next
    INDEX
    Explanations

    too late; gets smaller payments

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

    dynamically generated files

    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
    0.58
    }{
    0.52
    DATE
    0.52
    coln
    0.49
     AND
    0.48
    CO
    0.47
    VE
    0.46
    =
    0.46
    nd
    0.45
    ky
    0.45
    POSITIVE LOGITS
    发现
    0.50
     останавли
    0.47
     Cameras
    0.46
     Perimeter
    0.46
     નિર્ણય
    0.45
    农民
    0.44
    设定
    0.44
     balconies
    0.44
    cimentos
    0.43
     Polymers
    0.43
    Activations Density 0.003%

    No Known Activations