© 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. 23830
    Prev
    Next
    INDEX
    Explanations

    associated with

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

    associated with

    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
    ని
    0.84
    し
    0.74
    0.71
     人
    0.69
    ()=>{
    0.69
    कने
    0.67
    ీల
    0.67
     சம்பந்த
    0.67
    其他
    0.66
     forbindelse
    0.65
    POSITIVE LOGITS
    u
    1.01
     associated
    0.89
    ینگ
    0.88
    l
    0.86
    associated
    0.85
    t
    0.85
    ین
    0.80
    νή
    0.79
    ა
    0.78
    b
    0.77
    Activations Density 0.022%

    No Known Activations