© 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. 21575
    Prev
    Next
    INDEX
    Explanations

    time calculations and units

    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
     Ly
    0.49
     their
    0.47
     ly
    0.44
     G
    0.43
    ↵
    0.43
     Des
    0.43
     Saint
    0.43
    $
    0.42
     Exxon
    0.42
     Steven
    0.42
    POSITIVE LOGITS
    ையின்
    0.53
    াড়াও
    0.50
     위의
    0.49
    ␶
    0.48
     ግራም
    0.46
    ivasena
    0.46
     타입을
    0.46
    ྦ
    0.46
     aşağıdaki
    0.45
     métiers
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.