© 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. 241724
    Prev
    Next
    INDEX
    Explanations

    production value, copyright, preserved

    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
    ാര
    0.50
    یر
    0.50
    牖
    0.50
    ل
    0.49
    el
    0.49
    罗马
    0.47
    ohama
    0.47
    وپ
    0.46
    ıları
    0.46
     хора
    0.45
    POSITIVE LOGITS
     neto
    0.50
    ½
    0.49
     Zuck
    0.49
     contaminating
    0.46
     grew
    0.46
     reflecting
    0.45
     warrants
    0.45
     wrench
    0.44
    brushes
    0.44
     Zimmer
    0.43
    Activations Density 0.001%

    No Known Activations