© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21617
    Prev
    Next
    INDEX
    Explanations

    authenticity or genuineness

    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
     This
    -2.73
    kurtka
    -2.50
    
    -2.44
    bluza
    -2.42
    楦
    -2.42
    sukienka
    -2.38
     We
    -2.34
     marvelous
    -2.31
    鹛
    -2.30
     The
    -2.28
    POSITIVE LOGITS
    1
    2.95
    Although
    2.47
     ヶ
    2.41
     –
    2.30
    的一個
    2.30
    ),
    2.28
    すぎる
    2.25
    henswürdigkeiten
    2.23
    Surprisingly
    2.23
    ,.
    2.20
    Activations Density 0.002%

    No Known Activations