© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36520
    Prev
    Next
    INDEX
    Explanations

    directions and cross sections

    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
     malgré
    -1.32
    1
    -1.24
    ၎
    -1.17
     serons
    -1.13
     néer
    -1.11
     setEmail
    -1.08
    6
    -1.08
    焼く
    -1.07
     vertes
    -1.07
     maintenant
    -1.07
    POSITIVE LOGITS
     ''
    1.10
     which
    1.09
     Some
    1.07
     sorprendente
    1.01
     has
    1.01
    ("]");
    1.00
    河南
    0.99
     also
    0.97
     from
    0.96
     had
    0.96
    Activations Density 0.264%

    No Known Activations