© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 31069
    Prev
    Next
    INDEX
    Explanations

    human activities and analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     decorative
    0.48
    驱
    0.48
     conserver
    0.46
     reside
    0.46
     later
    0.46
     semaphore
    0.46
     witness
    0.45
     settimane
    0.45
     ceremony
    0.45
     successivo
    0.45
    POSITIVE LOGITS
     säga
    0.48
    ا
    0.48
     अधिक
    0.48
    比較
    0.47
     तुलना
    0.46
     момент
    0.46
    لات
    0.45
    шка
    0.45
     अंतर
    0.43
     срав
    0.43
    Activations Density 0.013%

    No Known Activations