© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38657
    Prev
    Next
    INDEX
    Explanations

    abbreviations followed by periods

    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
     monstru
    -1.09
    λίου
    -1.05
     dieselben
    -1.05
    酲
    -1.05
    Sprintf
    -1.04
     gada
    -1.04
    ichord
    -1.03
     enchant
    -1.02
     columbia
    -1.02
    íqu
    -1.00
    POSITIVE LOGITS
     have
    1.46
     this
    1.23
     more
    1.17
     so
    1.15
     there
    1.11
     in
    1.09
     new
    1.05
     up
    1.03
     such
    1.02
     where
    1.01
    Activations Density 0.018%

    No Known Activations