© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 59245
    Prev
    Next
    INDEX
    Explanations

    this X

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

    research, disable, learn

    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
    驸
    0.49
    螟
    0.45
     apprend
    0.43
    แห่ง
    0.43
     नियुक्ति
    0.42
    FileInputExcel
    0.42
    이자
    0.42
    罾
    0.42
     कन
    0.41
     назна
    0.41
    POSITIVE LOGITS
    packing
    0.51
    to
    0.45
    WELL
    0.45
    pl
    0.45
     ويمكن
    0.45
    ↵
    0.45
    {
    0.45
    }
    0.45
    FL
    0.43
     MTS
    0.43
    Activations Density 0.001%

    No Known Activations