© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73592
    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
     in
    -2.09
     by
    -1.98
    Although
    -1.88
    Those
    -1.85
     new
    -1.84
    Two
    -1.81
    angkap
    -1.81
    ꈊ
    -1.80
    Using
    -1.80
    After
    -1.80
    POSITIVE LOGITS
    ar
    2.16
    ............
    2.05
    ..........
    2.05
    he
    1.89
     respective
    1.84
    am
    1.83
     focuses
    1.83
    s
    1.82
    ​​​​​​​
    1.80
    i
    1.80
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.