© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72020
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ⅘
    -1.21
    趼
    -1.19
     disques
    -1.13
     connaissances
    -1.10
    őség
    -1.07
    klare
    -1.06
    removing
    -1.05
    kenal
    -1.03
    juego
    -1.02
     seguire
    -1.02
    POSITIVE LOGITS
    and
    1.14
    !
    1.09
    ---
    1.05
    や
    1.05
    一只
    1.02
    ’)
    1.01
     degli
    1.00
    !!!!!!
    0.98
     questi
    0.98
     usando
    0.98
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.