© 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. 42545
    Prev
    Next
    INDEX
    Explanations

    processed through

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

    technical instructions, foreign words, or specific entities

    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
     "${
    0.49
    ale
    0.49
    arlo
    0.48
    itley
    0.46
    ilt
    0.46
    úst
    0.46
    ild
    0.45
    ito
    0.45
    əd
    0.45
    :["
    0.44
    POSITIVE LOGITS
     инструментов
    0.59
     पुराने
    0.51
    㖡
    0.50
     refroidissement
    0.50
    럏
    0.49
     recouvre
    0.48
    วิธีการ
    0.47
    ﺫ
    0.47
     refroid
    0.47
     Instrum
    0.47
    Activations Density 0.000%

    No Known Activations