© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128650
    Prev
    Next
    INDEX
    Explanations

    occupy, occupancy, occupational

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    榈
    -3.30
    巖
    -3.19
    玙
    -2.89
     剤
    -2.81
    ſſel
    -2.80
    cables
    -2.69
    .”
    -2.69
    foglio
    -2.64
    orithm
    -2.50
     समीक्षाएं
    -2.48
    POSITIVE LOGITS
    1
    4.63
    3
    4.31
    0
    4.31
    2
    4.13
    4
    3.98
    8
    3.94
    7
    3.80
    9
    3.73
    5
    3.30
    6
    3.27
    Activations Density 0.007%

    No Known Activations