© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 116447
    Prev
    Next
    INDEX
    Explanations

    organizational roles

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

    followed by "and", "limits", "shirts", "Tile", "number"

    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
    uette
    0.47
     밝
    0.46
    ช่วง
    0.46
     Comfortable
    0.46
    чено
    0.45
     रेटिंग
    0.44
     Observations
    0.44
    แส
    0.44
     Datensch
    0.44
     Ratings
    0.44
    POSITIVE LOGITS
    ఎఫ్
    0.47
    ()'
    0.46
    FLY
    0.46
    ${
    0.45
     river
    0.45
    }}$,
    0.44
    :{
    0.44
     congregate
    0.44
    FAA
    0.44
     freighter
    0.43
    Activations Density 0.001%

    No Known Activations