© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71719
    Prev
    Next
    INDEX
    Explanations

    describing positive qualities

    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
     and
    -4.16
    และ
    -2.25
     allerlei
    -1.63
     fonctionnalités
    -1.63
     dáms
    -1.54
     및
    -1.52
     schuldig
    -1.50
     páns
    -1.49
     sillas
    -1.48
    upiter
    -1.47
    POSITIVE LOGITS
     of
    2.63
     in
    2.50
     for
    2.39
     when
    2.33
     on
    2.19
     at
    2.00
     this
    1.83
     before
    1.76
     from
    1.75
     after
    1.74
    Activations Density 0.072%

    No Known Activations