© 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. 774
    Prev
    Next
    INDEX
    Explanations

    Let's us

    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
    และ
    0.63
     ਅਤੇ
    0.63
     và
    0.56
     และ
    0.56
     หรือ
    0.56
     하지만
    0.56
    和
    0.56
     लेकिन
    0.55
     અને
    0.54
     혹은
    0.54
    POSITIVE LOGITS
     it
    1.00
     us
    0.78
     them
    0.77
     outsiders
    0.69
    它
    0.69
     everyone
    0.66
     people
    0.63
     perpetrators
    0.62
     THEM
    0.62
     nays
    0.61
    Activations Density 0.510%

    No Known Activations