© 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. 35034
    Prev
    Next
    INDEX
    Explanations

    name, date, or query labels

    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
     meub
    -1.27
     feltro
    -1.17
     desmotiv
    -1.04
     multicolore
    -1.03
     favorecer
    -1.02
    arrivo
    -1.02
     plásticos
    -1.01
    cellulose
    -1.01
     doivent
    -1.00
     všechny
    -0.99
    POSITIVE LOGITS
     so
    0.95
     if
    0.94
     panggilan
    0.93
     mostly
    0.90
     creates
    0.90
     name
    0.90
     Even
    0.87
    так
    0.87
     ikiwa
    0.85
     İl
    0.84
    Activations Density 0.022%

    No Known Activations