© 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. 42339
    Prev
    Next
    INDEX
    Explanations

    us make

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

    balance, UID, lack, myself, infrastructure

    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
    y
    0.49
     memorize
    0.47
     Kilometer
    0.45
     which
    0.44
     Risk
    0.44
     or
    0.43
     Interest
    0.43
     Shortcut
    0.43
    o
    0.43
     Av
    0.42
    POSITIVE LOGITS
     допомогти
    0.48
     сами
    0.47
    нять
    0.46
    URF
    0.46
    ട്ടി
    0.45
    ਾਨ
    0.45
    BackendAuth
    0.45
    hiddenMap
    0.45
    ั้ย
    0.44
     бути
    0.44
    Activations Density 0.000%

    No Known Activations