© 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. 127235
    Prev
    Next
    INDEX
    Explanations

    good at

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

    frequency and time

    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
    ت
    0.70
    ل
    0.52
    ار
    0.51
    friction
    0.50
    𝚕
    0.48
     Künst
    0.47
    ناسب
    0.46
    ص
    0.46
    حاد
    0.45
     মুন
    0.45
    POSITIVE LOGITS
     예
    0.51
     imponer
    0.49
     adapted
    0.46
     queremos
    0.46
     encephal
    0.46
    ｳ
    0.46
     कार्
    0.46
     estuary
    0.45
     bri
    0.45
     과거
    0.45
    Activations Density 0.000%

    No Known Activations