© 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. 54292
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    -1.10
     first
    -1.04
     only
    -0.98
     some
    -0.94
     time
    -0.93
     and
    -0.92
     increasing
    -0.91
     many
    -0.91
     with
    -0.91
     as
    -0.90
    POSITIVE LOGITS
     disponibilités
    1.14
     achats
    1.13
     préférences
    1.12
     perfeitamente
    1.09
     parfois
    1.09
    ネイル
    1.09
     mauvaises
    1.06
     éché
    1.06
    aucun
    1.05
    ulir
    1.02
    Activations Density 0.002%

    No Known Activations