© 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. 59505
    Prev
    Next
    INDEX
    Explanations

    working to ad Sky field

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

    beyond basic

    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
    鈮
    0.48
    苏
    0.44
    atoire
    0.43
    লিখিত
    0.41
     andra
    0.41
    导
    0.40
    ovalo
    0.39
     andere
    0.39
    atangan
    0.39
    ளிர்
    0.39
    POSITIVE LOGITS
    APPY
    0.47
     सकुशल
    0.45
    yielding
    0.45
     നേര
    0.43
    v
    0.42
     booze
    0.42
     faptul
    0.42
    unters
    0.41
     τρό
    0.41
     quieras
    0.41
    Activations Density 0.000%

    No Known Activations