© 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. 27274
    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
     despite
    -1.56
     both
    -1.45
     after
    -1.35
     several
    -1.34
     two
    -1.33
     ostensibly
    -1.30
     trying
    -1.28
     just
    -1.28
     numerous
    -1.25
     quickly
    -1.24
    POSITIVE LOGITS
     аудио
    1.23
    ఇ
    1.18
     грамм
    1.17
     случайно
    1.16
     [''],
    1.15
     verschiedener
    1.13
     provenant
    1.13
     festgelegt
    1.13
    Ų
    1.11
     SINGLE
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.