© 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. 197657
    Prev
    Next
    INDEX
    Explanations

    data, SOA, EXC, App

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

    states or contexts

    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
    ような
    0.52
    変わ
    0.51
     اقبال
    0.48
    ̀
    0.47
     Наталья
    0.46
    tte
    0.46
    Yap
    0.46
     രണ്ട്
    0.46
    tro
    0.45
    坪
    0.45
    POSITIVE LOGITS
     pads
    0.53
    áng
    0.47
     surgery
    0.46
     injured
    0.46
     blades
    0.46
    ەت
    0.45
     experts
    0.43
    सिन
    0.43
     buffers
    0.42
     गिर
    0.42
    Activations Density 0.000%

    No Known Activations