© 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. 9010
    Prev
    Next
    INDEX
    Explanations

    gcc benchmark METHOD

    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
     their
    -2.34
     it
    -1.89
     funcion
    -1.50
     being
    -1.48
     artesanía
    -1.46
    着她
    -1.45
     aéreo
    -1.45
     jaula
    -1.42
     motores
    -1.42
     its
    -1.41
    POSITIVE LOGITS
     also
    1.82
     также
    1.72
    Sinopse
    1.50
     彩色
    1.50
    Anche
    1.49
     แดง
    1.45
    Ϝ
    1.45
    ctuaries
    1.42
     poë
    1.40
     también
    1.39
    Activations Density 0.002%

    No Known Activations