© 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. 68494
    Prev
    Next
    INDEX
    Explanations

    application than, information that, deal by, process some

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

    biological and intellectual concepts

    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
    До
    0.54
     शनिवार
    0.52
     পোকামাকড়
    0.49
     जुड़ा
    0.48
     клю
    0.46
    ቧ
    0.46
     இடம்பெ
    0.46
    embourg
    0.45
     ম্যাচের
    0.45
     до
    0.44
    POSITIVE LOGITS
     ventures
    0.50
    5
    0.44
     erode
    0.43
    रान
    0.43
    EnableCOMDAT
    0.43
     scoping
    0.42
    ５
    0.42
     biological
    0.41
     næ
    0.41
     genomics
    0.41
    Activations Density 0.000%

    No Known Activations