© 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. 26000
    Prev
    Next
    INDEX
    Explanations

    web routing parameters

    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
     this
    -2.13
     before
    -1.57
     epitom
    -1.49
     greatly
    -1.48
     had
    -1.47
     more
    -1.47
     took
    -1.47
     difficult
    -1.44
     constantly
    -1.44
     first
    -1.42
    POSITIVE LOGITS
    instead
    1.44
    specifically
    1.43
     conséquences
    1.41
     régal
    1.34
     emporter
    1.33
     demandes
    1.30
    might
    1.30
    actually
    1.29
     horrid
    1.28
     évidemment
    1.28
    Activations Density 0.001%

    No Known Activations