© 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. 67884
    Prev
    Next
    INDEX
    Explanations

    game characters and 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_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
     Flexib
    -1.28
    اء
    -1.20
     mentales
    -1.20
    到底是
    -1.18
     外観
    -1.17
     its
    -1.17
    هاي
    -1.17
     ASSOCIATES
    -1.17
     девочки
    -1.15
     secrétaire
    -1.15
    POSITIVE LOGITS
     to
    1.37
     game
    1.30
     скульп
    1.23
     
    1.20
    </h2>
    1.18
     possible
    1.17
    boxed
    1.14
    /">
    1.14
    ystis
    1.13
    </h1>
    1.12
    Activations Density 0.003%

    No Known Activations