© 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. 9711
    Prev
    Next
    INDEX
    Explanations

    prison, inmate, prisoner

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

    prison, inmates, 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
    Hunting
    0.46
    Parking
    0.43
    畋
    0.42
    hunting
    0.41
    郊
    0.40
     Hunting
    0.40
     শিকার
    0.39
    柰
    0.38
    र्निंग
    0.38
     stalk
    0.37
    POSITIVE LOGITS
     inmate
    1.41
     inmates
    1.39
     prison
    1.38
     prisoners
    1.34
     Prison
    1.34
    Prison
    1.30
     prisoner
    1.27
     Prisoners
    1.27
     prisons
    1.23
    prison
    1.17
    Activations Density 0.157%

    No Known Activations