© 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. 12520
    Prev
    Next
    INDEX
    Explanations

    http:// or https://

    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
     for
    -1.48
     such
    -1.23
     because
    -1.23
     even
    -1.17
     in
    -1.07
     with
    -1.05
     (
    -1.00
     begin
    -1.00
     having
    -0.96
     all
    -0.94
    POSITIVE LOGITS
     verdaderos
    1.21
    tiendo
    1.18
     discuter
    1.15
     aktiviteter
    1.14
     mojej
    1.13
     nossos
    1.09
     zimowa
    1.09
     coû
    1.08
     niedersachsen
    1.07
     trám
    1.07
    Activations Density 0.009%

    No Known Activations