© 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. 24201
    Prev
    Next
    INDEX
    Explanations

    quantities of

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

    piping, parts, filter, theme, pipes

    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
    is
    0.55
    侮
    0.49
    ar
    0.46
    <0x92>
    0.44
    to
    0.44
    ji
    0.44
     vastly
    0.44
    ro
    0.43
    ser
    0.43
     insurgency
    0.43
    POSITIVE LOGITS
     একখানি
    0.58
     ব্যবহারের
    0.57
    စိတ်အပိုင်း
    0.56
     Tarifleri
    0.55
     Bedürfn
    0.54
     電話
    0.53
     進
    0.52
     گوئی
    0.51
     deberán
    0.51
     Bedürfnisse
    0.50
    Activations Density 0.000%

    No Known Activations