© 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. 39521
    Prev
    Next
    INDEX
    Explanations

    arrested or detained

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

    unjust arrest and detention

    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
    Calories
    0.49
     कैलो
    0.48
    calories
    0.47
    利
    0.46
    Organic
    0.45
     kalor
    0.45
    燥
    0.45
     calorie
    0.44
     calories
    0.44
    菜
    0.44
    POSITIVE LOGITS
     unjustly
    0.95
     detained
    0.92
     imprisonment
    0.91
     detention
    0.90
     unjust
    0.88
     arrested
    0.87
     हिरासत
    0.86
     injust
    0.84
     गिरफ्तार
    0.84
     arrest
    0.83
    Activations Density 0.079%

    No Known Activations