© 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. 196361
    Prev
    Next
    INDEX
    Explanations

    Gin Guide

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

    technical documentation and 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
    ’),
    0.54
     remit
    0.49
    把它
    0.46
    པ
    0.46
    的名
    0.46
    '),
    0.43
     permitir
    0.43
    ’).
    0.42
     permit
    0.42
     decrypt
    0.42
    POSITIVE LOGITS
     Boley
    0.49
    쁠
    0.49
    쥬
    0.48
    స్కీ
    0.47
    우스
    0.47
     Gọi
    0.47
     junge
    0.47
     natürliche
    0.47
     ски
    0.46
    urdu
    0.46
    Activations Density 0.001%

    No Known Activations