© 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. 65973
    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
    ムラ
    -1.07
     ogr
    -1.01
     vocales
    -1.01
     soyez
    -1.01
     university
    -1.00
     échou
    -1.00
     voyant
    -0.99
    イレ
    -0.99
     reż
    -0.98
     tantôt
    -0.96
    POSITIVE LOGITS
     makeshift
    0.94
     хотя
    0.88
    定食
    0.88
    CastException
    0.83
     innumerable
    0.82
    ')}}"
    0.82
    ńskiego
    0.81
     only
    0.80
    <0xA3>
    0.79
    Boxscore
    0.79
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.