© 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. 40692
    Prev
    Next
    INDEX
    Explanations

    working at, when you, together we

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

    making text concise

    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
     cuerpos
    0.47
     reproduct
    0.47
     proceder
    0.47
     absol
    0.45
     materially
    0.45
    re
    0.45
     exportation
    0.45
    <unused693>
    0.43
     construir
    0.43
    نيه
    0.42
    POSITIVE LOGITS
    𝚢
    0.52
    𝚎
    0.48
     वायरिंग
    0.48
     Arrows
    0.47
     lube
    0.46
    lamps
    0.46
    quakes
    0.45
    暖かい
    0.45
    ツ
    0.45
    tractor
    0.44
    Activations Density 0.000%

    No Known Activations