© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12828
    Prev
    Next
    INDEX
    Explanations

    main function call

    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
     parceria
    0.81
     Partnerships
    0.77
     partenariat
    0.73
     partnerships
    0.69
    partnership
    0.68
     partnership
    0.66
     Partnership
    0.64
    协
    0.64
     menjal
    0.57
     collaborations
    0.56
    POSITIVE LOGITS
    ;
    0.60
    不知道
    0.58
     vibe
    0.58
    ;(
    0.54
     Niet
    0.53
     Frankenstein
    0.53
    ;<
    0.52
     vogue
    0.52
    】【
    0.50
     Avatar
    0.50
    Activations Density 0.000%

    No Known Activations