© 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. 227050
    Prev
    Next
    INDEX
    Explanations

    choice to

    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
    覦
    0.61
    变化
    0.59
    আর
    0.53
    猷
    0.49
    ත්‍ර
    0.48
    ﻪ
    0.48
     descriptions
    0.48
    니어
    0.47
    姐姐
    0.47
    较高
    0.47
    POSITIVE LOGITS
    ante
    0.55
    ada
    0.52
    egen
    0.50
     )
    0.48
    eli
    0.48
    oh
    0.47
    umble
    0.47
    elecimento
    0.47
    ela
    0.46
    ing
    0.46
    Activations Density 0.000%

    No Known Activations