© 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. 22-GEMMASCOPE-RES-131K
    7. 72651
    Prev
    Next
    INDEX
    Explanations

    Swift, Account, Stonyx, Familial

    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_22/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
    Sqft
    -1.20
     Periode
    -1.05
    ´)
    -1.04
    intosh
    -1.02
    Señor
    -1.00
     Kanada
    -0.99
     PÅ
    -0.99
    PRM
    -0.98
     agus
    -0.97
     baru
    -0.97
    POSITIVE LOGITS
     -
    1.14
    ]$,
    1.01
     nhung
    0.94
    出声
    0.91
    例如
    0.90
     garantías
    0.89
     такая
    0.87
     tuong
    0.87
     совершен
    0.87
     each
    0.87
    Activations Density 0.001%

    No Known Activations