© 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. 168504
    Prev
    Next
    INDEX
    Explanations

    Nexus, liberty, origins

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

    describing qualities or related items

    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
    зумі
    0.49
    (
    0.48
    <0x80>
    0.48
     ating
    0.47
    described
    0.47
    0.46
    podcast
    0.46
    r
    0.46
    the
    0.45
    paran
    0.44
    POSITIVE LOGITS
     મહિલા
    0.52
     নাচ
    0.50
     एकल
    0.49
     വനി
    0.49
     पब्लिक
    0.48
     Ичиго
    0.48
     Теннис
    0.48
     Dolphins
    0.47
     የተለያዩ
    0.47
     Taxation
    0.47
    Activations Density 0.000%

    No Known Activations