© 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. 96881
    Prev
    Next
    INDEX
    Explanations

    money, seven, advise

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

    focusing on specific terms and parameters

    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
    েরই
    0.47
    বেল
    0.46
    릭
    0.46
    ⍵
    0.45
     Nantucket
    0.45
    พ
    0.45
    ₮
    0.44
    saxophone
    0.44
     डैम
    0.44
     недо
    0.43
    POSITIVE LOGITS
    ير
    0.52
    *{-
    0.45
    苑
    0.45
     aidant
    0.44
    瞄
    0.44
    أي
    0.44
    Navigation
    0.43
     secu
    0.43
     ×
    0.43
     tomon
    0.43
    Activations Density 0.001%

    No Known Activations