© 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. 10921
    Prev
    Next
    INDEX
    Explanations

    consists of a

    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
     to
    -1.87
     through
    -1.84
     would
    -1.69
     during
    -1.66
     while
    -1.58
     might
    -1.55
     in
    -1.45
     can
    -1.43
     did
    -1.39
     on
    -1.37
    POSITIVE LOGITS
     appels
    1.60
     simpel
    1.41
     recommandations
    1.40
     tirs
    1.35
     balkon
    1.32
     automobili
    1.32
     botines
    1.28
     parfums
    1.27
     praktis
    1.27
     dokter
    1.25
    Activations Density 0.073%

    No Known Activations