© 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. 42869
    Prev
    Next
    INDEX
    Explanations

    time and measurements

    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
     Such
    -2.69
    also
    -2.67
     Obtén
    -2.58
     όταν
    -2.58
     Also
    -2.53
     Months
    -2.52
     Ensuring
    -2.52
    since
    -2.52
    including
    -2.45
    “
    -2.45
    POSITIVE LOGITS
    0
    2.88
    .”
    2.44
     然
    2.33
    鑁
    2.31
    .\\
    2.27
     \_
    2.25
    蜘
    2.20
    浿
    2.17
    却不
    2.17
    佻
    2.16
    Activations Density 0.175%

    No Known Activations