© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 190052
    Prev
    Next
    INDEX
    Explanations

    subject, community, monitor, member, battery, dumpster

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

    building embeddings

    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
    it
    0.52
    é
    0.52
     Wien
    0.51
    ain
    0.50
     Zagreb
    0.50
    ín
    0.47
     Norden
    0.47
    َت
    0.46
     Hör
    0.46
     Í
    0.46
    POSITIVE LOGITS
    dut
    0.46
    depression
    0.46
    drawLine
    0.45
    লী
    0.45
    keyValue
    0.44
    geoLocation
    0.44
    的代码
    0.44
    DBObject
    0.43
     doloribus
    0.43
    schema
    0.43
    Activations Density 0.000%

    No Known Activations