© 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. 100961
    Prev
    Next
    INDEX
    Explanations

    Analysis of

    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
     to
    -2.19
     
    -1.97
     ciencias
    -1.94
    ↵
    -1.90
    自体
    -1.89
    ☫
    -1.82
     who
    -1.82
     which
    -1.80
     která
    -1.76
     (
    -1.72
    POSITIVE LOGITS
    </strong>
    2.58
    軼
    2.44
    those
    2.28
    _
    2.22
    _{
    2.20
    after
    2.16
    erweise
    2.16
    诙
    2.08
     мальчика
    2.03
    経緯
    2.00
    Activations Density 0.135%

    No Known Activations