© 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. 31753
    Prev
    Next
    INDEX
    Explanations

    a followed by articles/descriptors

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

    depending on

    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
    پ
    0.55
    urp
    0.53
    C
    0.50
    F
    0.50
    B
    0.48
    所以
    0.48
    {
    0.47
    وق
    0.46
    ور
    0.45
    प
    0.44
    POSITIVE LOGITS
     legislator
    0.53
     特定
    0.50
     FAX
    0.49
     Stages
    0.48
     Bibliography
    0.47
     ప్రజా
    0.47
     politician
    0.47
     WLAN
    0.46
     সপ্তাহ
    0.46
     الهاتف
    0.46
    Activations Density 0.000%

    No Known Activations