© 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. 40663
    Prev
    Next
    INDEX
    Explanations

    programming versioning keywords

    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
    </h3>
    -1.50
    じた
    -1.08
    fungsi
    -1.06
    ···
    -1.06
    artigen
    -1.01
     ライ
    -1.00
    pustakaan
    -0.97
    斯
    -0.96
     liquido
    -0.95
     pakket
    -0.95
    POSITIVE LOGITS
    幼稚
    1.20
     Запад
    1.19
     meios
    1.14
    новение
    1.13
    AsUp
    1.13
    toContain
    1.11
    情侣
    1.11
    PhysRevLett
    1.09
    ugais
    1.09
    そこに
    1.09
    Activations Density 0.150%

    No Known Activations