© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28059
    Prev
    Next
    INDEX
    Explanations

    case citations numbers

    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
     restent
    -0.90
    עים
    -0.89
    svn
    -0.85
     Luiz
    -0.83
    nerstag
    -0.82
     cing
    -0.78
     endl
    -0.78
    ⠦
    -0.78
     TRIB
    -0.77
     Tribunal
    -0.77
    POSITIVE LOGITS
     Fahrrad
    0.88
     your
    0.88
    lipas
    0.83
    getDriver
    0.82
    titanic
    0.82
     Sorten
    0.81
     siebie
    0.79
     sexuality
    0.79
    Maryland
    0.78
     rozwiąz
    0.78
    Activations Density 0.006%

    No Known Activations