© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 485
    Prev
    Next
    INDEX
    Explanations

    numeric ranges

    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_22/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
     PARENTS
    -0.86
     Depreciation
    -0.85
     פשוט
    -0.83
     "..\..\..\
    -0.82
     lotion
    -0.82
    griffen
    -0.81
    Prophet
    -0.81
    corbic
    -0.81
    MediaType
    -0.81
    Checker
    -0.80
    POSITIVE LOGITS
     accurate
    1.51
     precision
    1.45
     precise
    1.38
     accuracy
    1.35
     accurately
    1.27
     Precise
    1.26
    precision
    1.23
    Precision
    1.19
     Precision
    1.19
    精确
    1.16
    Activations Density 0.095%

    No Known Activations