© 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. 204836
    Prev
    Next
    INDEX
    Explanations

    wild herds

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

    explain the AI's limitations

    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
     hoja
    0.54
     propiedad
    0.48
     сотрудник
    0.48
     palmit
    0.47
    برای
    0.47
    悆
    0.47
    细菌
    0.46
     insanların
    0.46
     hastalık
    0.46
    ாத
    0.46
    POSITIVE LOGITS
    Tier
    0.43
    Mess
    0.43
    of
    0.42
     meals
    0.39
    Tile
    0.38
    T
    0.38
     їх
    0.37
     コー
    0.37
    Child
    0.37
    Burger
    0.36
    Activations Density 0.001%

    No Known Activations