© 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. 67977
    Prev
    Next
    INDEX
    Explanations

    variable names and 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
     of
    -2.97
     for
    -2.27
     also
    -1.97
     to
    -1.73
     always
    -1.52
     that
    -1.47
     altijd
    -1.45
    ☡
    -1.44
     vna
    -1.37
     desain
    -1.34
    POSITIVE LOGITS
     možné
    1.52
     efectuar
    1.47
     acelerar
    1.46
    c
    1.44
     abandonar
    1.43
     —
    1.43
     incorporar
    1.42
    8
    1.41
     одной
    1.41
     ajustar
    1.39
    Activations Density 0.062%

    No Known Activations