© 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. 58677
    Prev
    Next
    INDEX
    Explanations

    compiler prefixes: _MSC_, _WIN3

    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
     provocando
    -2.23
     causando
    -2.08
     erzielt
    -1.93
     posando
    -1.84
     acompañada
    -1.80
     puramente
    -1.77
     evitando
    -1.75
     contando
    -1.74
     parcialmente
    -1.70
     resultaat
    -1.66
    POSITIVE LOGITS
    3
    2.47
    5
    2.31
    6
    2.23
    7
    2.20
    2
    2.13
    9
    2.00
    1
    1.98
    ↵
    1.95
     of
    1.86
    8
    1.80
    Activations Density 0.013%

    No Known Activations