© 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. 74385
    Prev
    Next
    INDEX
    Explanations

    connected to or between

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

    consequences, arrest, jail

    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
     Zuge
    0.50
     Ừ
    0.49
     Terbaru
    0.49
    ępnie
    0.47
     karış
    0.47
    ियंस
    0.47
    演技
    0.47
    丨
    0.46
     மாசுபா
    0.46
     Comfortable
    0.46
    POSITIVE LOGITS
     external
    0.60
     externa
    0.53
     this
    0.51
     externally
    0.51
     secondary
    0.50
    external
    0.49
     google
    0.49
    EXTERNAL
    0.48
     rectangular
    0.46
     minors
    0.46
    Activations Density 0.001%

    No Known Activations