© 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. 57841
    Prev
    Next
    INDEX
    Explanations

    > at the proper place

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

    AI-Powered Autocompletion, augmentation, and requirements

    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
    מש
    0.50
    贾
    0.49
    QTTR
    0.48
    ITTLE
    0.48
    gunakan
    0.47
     पुरुष
    0.47
    தள
    0.47
    ッサージ
    0.46
    മ
    0.46
    割引
    0.46
    POSITIVE LOGITS
     Camps
    0.54
     Ch
    0.52
     Review
    0.50
     Côte
    0.50
     village
    0.50
     Respir
    0.50
     كافة
    0.48
     Zone
    0.47
     Merino
    0.46
     Cote
    0.46
    Activations Density 0.000%

    No Known Activations