© 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. 146005
    Prev
    Next
    INDEX
    Explanations

    architecture

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

    video intros

    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
     disappro
    0.55
     punishable
    0.47
     finitely
    0.46
    зино
    0.46
    ього
    0.45
     frustrating
    0.44
     shameful
    0.43
    🅽
    0.43
    িয়া
    0.43
    дки
    0.43
    POSITIVE LOGITS
     architect
    0.59
     instrument
    0.44
    人形
    0.44
     isOpen
    0.43
    鼍
    0.43
     Architecture
    0.43
     infrastrukt
    0.43
    wini
    0.42
     Instrument
    0.42
     instrumentation
    0.41
    Activations Density 0.000%

    No Known Activations