© 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. 88291
    Prev
    Next
    INDEX
    Explanations

    Airbnb of energy

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

    initialization and technical terms

    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
    тер
    0.44
    名
    0.44
    աշ
    0.43
     (
    0.42
     profession
    0.42
     consortium
    0.42
    的名
    0.41
    ames
    0.41
     famous
    0.41
    팔
    0.41
    POSITIVE LOGITS
    DummyView
    0.52
     Agua
    0.52
    ÁS
    0.52
     Gameplay
    0.50
    Durante
    0.49
    Banco
    0.47
    ENCI
    0.47
     płyt
    0.47
    Gameplay
    0.47
    IC
    0.46
    Activations Density 0.002%

    No Known Activations