© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10110
    Prev
    Next
    INDEX
    Explanations

    import java.util

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
    reservation
    0.67
    fan
    0.63
     reservation
    0.63
    clock
    0.63
    ch
    0.63
    toxicity
    0.61
     tag
    0.60
    ต
    0.60
    ke
    0.59
    card
    0.59
    POSITIVE LOGITS
    SUMMARY
    0.62
    াতাড়ি
    0.61
     SUMMARY
    0.59
     Editorial
    0.59
    ņi
    0.59
     आतंकियों
    0.57
     MILLER
    0.57
     Reveals
    0.57
     Jocelyn
    0.57
     diminishes
    0.57
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.