© 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. 26670
    Prev
    Next
    INDEX
    Explanations

    calling parent methods

    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
    uniqlo
    -1.13
    ですので
    -1.09
    んじゃ
    -1.06
    헷
    -1.05
    幃
    -1.04
     gradova
    -1.03
     those
    -1.02
     extinción
    -1.01
     consentimento
    -1.00
    古屋
    -0.98
    POSITIVE LOGITS
    1.32
     bedste
    1.04
     flesta
    1.02
     jedoch
    0.97
    のも
    0.92
    ]$.
    0.91
     senaste
    0.91
     umani
    0.91
     recognised
    0.90
     uttry
    0.90
    Activations Density 0.002%
    No Known Activations