© 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. 30778
    Prev
    Next
    INDEX
    Explanations

    solving application code

    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
     Beyonce
    0.51
     第二
    0.48
     電
    0.47
     套
    0.47
     一个
    0.46
     another
    0.45
     什么
    0.44
     quantized
    0.43
     两
    0.43
     ">
    0.43
    POSITIVE LOGITS
    Rajas
    0.51
    Analysts
    0.47
    Testing
    0.46
    Kum
    0.44
    cultures
    0.43
     analysts
    0.42
    Mal
    0.42
    Impact
    0.41
    irk
    0.40
     Analysts
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.