© 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. 248469
    Prev
    Next
    INDEX
    Explanations

    stage pizza

    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
    w
    0.54
     Schroeder
    0.46
     region
    0.45
     Brennan
    0.44
     Snyder
    0.44
    হারে
    0.43
     Kunststoff
    0.43
     khẳng
    0.42
     összef
    0.42
     Schreiber
    0.42
    POSITIVE LOGITS
    罨
    0.46
    だろう
    0.43
    ৃষ্ট
    0.42
    וי
    0.41
    齟
    0.41
    חר
    0.40
     ট্র্যাক
    0.40
    विद
    0.40
     সাবধান
    0.39
    也有
    0.39
    Activations Density 0.001%

    No Known Activations