© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60082
    Prev
    Next
    INDEX
    Explanations

    is followed by state or property

    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
    INTAIN
    -1.76
     даже
    -1.50
    蒾
    -1.47
    }%
    -1.46
     rağmen
    -1.46
     kunna
    -1.45
    Chasing
    -1.45
    tijden
    -1.43
     even
    -1.41
    enzuela
    -1.39
    POSITIVE LOGITS
    .
    1.38
     ところ
    1.30
     particularmente
    1.29
     lèvres
    1.27
    慙
    1.26
     étages
    1.24
    achau
    1.23
    replaced
    1.20
    了几
    1.20
    utzt
    1.20
    Activations Density 0.021%

    No Known Activations