© 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. 33187
    Prev
    Next
    INDEX
    Explanations

    HTML structure and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ！(
    -1.32
     to
    -1.23
     in
    -1.08
    ？　
    -1.03
    ！（
    -1.01
    ～！
    -1.00
    fourths
    -0.99
    thirds
    -0.98
     by
    -0.95
    ichtet
    -0.95
    POSITIVE LOGITS
    為に
    1.09
     rispar
    1.02
     achats
    0.97
    Causas
    0.97
    ほとん
    0.97
    Reduc
    0.96
     wielu
    0.95
    ふわ
    0.94
    hombres
    0.94
     gemak
    0.92
    Activations Density 0.051%

    No Known Activations