© 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. 10-GEMMASCOPE-RES-131K
    7. 11130
    Prev
    Next
    INDEX
    Explanations

    movie and game titles

    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
    ísticas
    -1.16
    ⋀
    -1.14
    chalten
    -1.13
     tirantes
    -1.11
    chafft
    -1.09
    ena
    -1.08
    ennheiser
    -1.08
     in
    -1.08
     perlas
    -1.06
    Ϳ
    -1.06
    POSITIVE LOGITS
     need
    1.32
     letz
    1.27
    already
    1.08
    efec
    1.06
     mię
    1.06
     koniecz
    1.05
    valry
    1.05
     Auflösung
    1.05
     example
    1.04
     already
    1.04
    Activations Density 0.023%

    No Known Activations