© 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. 68821
    Prev
    Next
    INDEX
    Explanations

    climate conditionstracing papernightlifenetwork services

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

    main, wavelength, extremely, red, unintentional, electromagnetic

    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
    ペン
    0.52
    発表
    0.50
    чено
    0.47
    ал
    0.47
    ファン
    0.46
    ﾙ
    0.46
    Ｊ
    0.45
    нок
    0.45
    ді
    0.45
     пациента
    0.45
    POSITIVE LOGITS
     لأنه
    0.49
     velit
    0.47
     است
    0.46
     Turf
    0.45
     ကျွန်
    0.45
     Blond
    0.45
     Dating
    0.44
     Football
    0.44
    ​​​​
    0.44
     Crimes
    0.44
    Activations Density 0.002%

    No Known Activations