© 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. 107666
    Prev
    Next
    INDEX
    Explanations

    insurance policy adjustments

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

    data management and analytics

    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
    createInfo
    0.44
    К
    0.43
    入
    0.43
    निय
    0.43
    死了
    0.41
    Ка
    0.41
    práv
    0.41
    착
    0.41
    یس
    0.41
    zd
    0.41
    POSITIVE LOGITS
     Alibaba
    0.46
     ওই
    0.46
     supers
    0.45
     reunion
    0.45
     unrival
    0.45
     優
    0.45
     SQL
    0.44
     kidn
    0.44
     ransom
    0.44
     abduction
    0.44
    Activations Density 0.003%

    No Known Activations