© 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. 172278
    Prev
    Next
    INDEX
    Explanations

    material properties and descriptions

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

    strategy and business concepts

    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
     boasts
    0.52
     sigue
    0.50
     muestra
    0.48
     alcanz
    0.47
     amalgam
    0.46
    ,|\
    0.46
     ผ้า
    0.46
     dispone
    0.46
     ค
    0.46
     scant
    0.45
    POSITIVE LOGITS
    資金
    0.46
    పే
    0.45
    輸
    0.43
     Startup
    0.43
    战略
    0.42
     Winning
    0.41
     Shift
    0.40
    vý
    0.40
     inputFile
    0.40
    術
    0.40
    Activations Density 0.000%

    No Known Activations