© 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. 109648
    Prev
    Next
    INDEX
    Explanations

    dispute; apprenticeships; fusion

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

    understanding these

    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
    atan
    0.49
    enem
    0.49
    ختلف
    0.48
    ichten
    0.48
    ،
    0.48
    '
    0.47
    ultur
    0.47
    اين
    0.47
     complica
    0.46
    、
    0.46
    POSITIVE LOGITS
     ஒப்பு
    0.45
     Fusion
    0.45
     Appalach
    0.44
     apprenticeship
    0.43
     limp
    0.42
     DISPLAY
    0.42
     Apprentice
    0.42
    ћин
    0.42
     infringing
    0.42
    shoe
    0.41
    Activations Density 0.000%

    No Known Activations