© 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. 22-GEMMASCOPE-RES-131K
    7. 35513
    Prev
    Next
    INDEX
    Explanations

    units 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_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
     /$
    -1.05
    leq
    -1.05
     EconPapers
    -1.04
    öng
    -1.04
     apreci
    -1.04
    BitConverter
    -1.03
    rento
    -1.02
    xtype
    -1.02
    IndentedString
    -1.02
    FontAwesomeIcon
    -1.01
    POSITIVE LOGITS
     flesta
    1.06
     entusiasmo
    1.02
    そのため
    1.02
    鉛筆
    0.99
    タブ
    0.99
    谆
    0.99
    動機
    0.98
    変わらず
    0.98
     detalj
    0.97
     meistens
    0.97
    Activations Density 0.008%

    No Known Activations