© 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. 198278
    Prev
    Next
    INDEX
    Explanations

    animal models, live cultures, or stallion

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

    instructions, rules, or choices

    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
    <unused410>
    0.48
    isVisible
    0.47
    <unused282>
    0.47
     entstand
    0.45
     جائیں
    0.44
    ු
    0.44
    ཟ
    0.43
     rougeâtres
    0.43
     elektromagnet
    0.43
    と呼ば
    0.42
    POSITIVE LOGITS
     a
    0.57
     {
    0.52
     to
    0.50
     help
    0.49
     SG
    0.48
     purch
    0.47
     Node
    0.47
     VMware
    0.47
     nodes
    0.47
     non
    0.46
    Activations Density 0.000%

    No Known Activations