© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 146568
    Prev
    Next
    INDEX
    Explanations

    Tagged Alfred, marked with, as Special, Chapter

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

    global affairs and business

    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
    བ་
    0.47
    eraser
    0.45
     этапе
    0.44
     斜
    0.44
    剃
    0.44
    রিত
    0.44
     संबोध
    0.44
    өх
    0.43
     पाठ
    0.42
    шенный
    0.42
    POSITIVE LOGITS
    Tourism
    0.48
    Networking
    0.44
    DEVELOP
    0.44
     mind
    0.44
    embangunan
    0.44
    ...
    0.43
     TRANSPORT
    0.43
     "
    0.42
     constraint
    0.42
     מי
    0.42
    Activations Density 0.001%

    No Known Activations