© 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. 9264
    Prev
    Next
    INDEX
    Explanations

    form of, up to

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

    coffee grounds or Python

    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
    {
    0.61
     temperature
    0.58
    <0x80>
    0.56
    ↵↵
    0.55
     manufacturer
    0.50
    此
    0.50
     make
    0.49
    (
    0.49
     paradise
    0.48
     este
    0.48
    POSITIVE LOGITS
    ĝ
    0.54
     برقرار
    0.53
     शख
    0.51
     ஆன
    0.51
    gaan
    0.51
     தடு
    0.50
    昛
    0.50
     ஆதார
    0.49
    jahteraan
    0.49
    <unused1055>
    0.49
    Activations Density 0.000%

    No Known Activations