© 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. 24643
    Prev
    Next
    INDEX
    Explanations

    articles, phrases, or descriptions

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

    planets, control, walking, pop, fabric, crops, plastic, Portal

    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
    älfte
    0.45
     שנה
    0.44
    ม
    0.44
    嫒
    0.44
    ед
    0.43
    א
    0.43
    י
    0.43
    잤
    0.43
    Tecla
    0.42
    от
    0.41
    POSITIVE LOGITS
     Hu
    0.50
     plus
    0.49
     missiles
    0.48
     Plus
    0.47
     hu
    0.45
     Patriots
    0.45
     Jesuits
    0.44
     insurgents
    0.44
     KGB
    0.44
     Mohammed
    0.44
    Activations Density 0.173%

    No Known Activations