© 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. 10-GEMMASCOPE-RES-131K
    4. 69435
    Prev
    Next
    INDEX
    Explanations

    years and dates

    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_10/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
     in
    -2.52
     when
    -2.47
     with
    -2.33
     by
    -2.05
     all
    -1.93
     not
    -1.88
    on
    -1.85
     if
    -1.82
     after
    -1.80
     and
    -1.80
    POSITIVE LOGITS
     réve
    1.83
    𝐒
    1.82
     lavable
    1.73
     hés
    1.72
     protéger
    1.67
    衚
    1.64
    Gucci
    1.63
     remé
    1.61
     terminer
    1.60
     nació
    1.58
    Activations Density 0.328%

    No Known Activations