© 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. 15475
    Prev
    Next
    INDEX
    Explanations

    birth

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

    install, include, auto, mode, redesign

    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
    信息化
    0.51
    code
    0.50
    ab
    0.49
                
    0.48
    ev
    0.48
    d
    0.47
    cd
    0.47
    digital
    0.46
    h
    0.46
    do
    0.43
    POSITIVE LOGITS
     istedi
    0.57
     bạn
    0.57
     vuole
    0.57
     شما
    0.54
     oček
    0.53
     pantalones
    0.51
     gewüns
    0.50
     Hotels
    0.50
     nariz
    0.49
     jūs
    0.49
    Activations Density 0.000%

    No Known Activations