© 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. 130340
    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
    ;
    -1.25
    が
    -1.21
    淵
    -1.17
     stycznia
    -1.15
     Agustus
    -1.15
     Ağustos
    -1.14
    $/
    -1.12
     ۱۱
    -1.10
     Desember
    -1.09
     ۱۷
    -1.09
    POSITIVE LOGITS
    参考にして
    1.21
     ず
    1.17
    Mitglied
    1.16
     it
    1.16
    љено
    1.13
    亳
    1.13
    unked
    1.08
    ちな
    1.08
    参见
    1.07
    ｱ
    1.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.