© 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. 31158
    Prev
    Next
    INDEX
    Explanations

    things had

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

    Tasers, SQL injection, Maverick, Muslims, historical systems

    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
    স
    0.58
     준비
    0.50
    ان
    0.50
     사이에
    0.49
    vide
    0.48
    offers
    0.46
    ن
    0.46
    ange
    0.45
    BI
    0.45
    ক
    0.45
    POSITIVE LOGITS
     ```
    0.50
     indoct
    0.48
     androidx
    0.47
    ድር
    0.47
     hijacked
    0.46
     bookstore
    0.46
     workbench
    0.46
     doctrinal
    0.45
     aard
    0.45
     discharged
    0.45
    Activations Density 0.000%

    No Known Activations