© 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. 227458
    Prev
    Next
    INDEX
    Explanations

    joint, carrying, agreements, weapons

    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
    AD
    0.46
    *=
    0.45
     nový
    0.44
    น
    0.43
     ns
    0.42
     perspective
    0.42
    perspective
    0.41
     hair
    0.40
    BLINK
    0.40
    {~
    0.40
    POSITIVE LOGITS
     মাঝামা
    0.51
    悱
    0.49
     Rous
    0.49
     Wochschr
    0.49
    跄
    0.49
    VideoButton
    0.47
     Xcode
    0.47
     پھیل
    0.47
     Scri
    0.47
    辉
    0.47
    Activations Density 0.002%

    No Known Activations