© 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. 3615
    Prev
    Next
    INDEX
    Explanations

    specific identifiers and their context

    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
    ?”
    -2.27
     esclusivamente
    -2.14
    dámské
    -2.09
    ”
    -2.03
    ”?
    -2.00
    ;”
    -1.98
     sugli
    -1.96
    輒
    -1.93
     -}
    -1.91
     バター
    -1.91
    POSITIVE LOGITS
     you
    2.27
    蚡
    2.22
    gucig
    2.22
    踯
    2.20
    并非
    2.11
    跑去
    1.98
    CHREIB
    1.98
    ⢱
    1.94
    은
    1.91
    ⎔
    1.90
    Activations Density 0.000%

    No Known Activations