© 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. 161317
    Prev
    Next
    INDEX
    Explanations

    coverage, development, format

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

    chemical compounds and amounts

    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
     साम्राज्य
    0.52
     बुरा
    0.48
     पहा
    0.47
    roma
    0.46
     فونبټ
    0.46
    ☓
    0.46
    ENTE
    0.46
     घोड़ा
    0.46
     வெங்க
    0.46
    🗡
    0.45
    POSITIVE LOGITS
    (
    0.49
     carbonate
    0.48
     essai
    0.48
     activ
    0.48
     cartons
    0.46
     aque
    0.46
     dispensers
    0.46
     cements
    0.45
     antics
    0.45
     calculators
    0.45
    Activations Density 0.001%

    No Known Activations