© 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. 66624
    Prev
    Next
    INDEX
    Explanations

    discovering new possibilities

    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
     allzu
    -1.08
     cualquier
    -1.00
    好きな
    -0.97
     fuß
    -0.97
     любы
    -0.96
     perfetto
    -0.93
     gesprochen
    -0.92
     dilengkapi
    -0.91
     zawsze
    -0.91
     or
    -0.91
    POSITIVE LOGITS
     possibilities
    1.60
     possibilité
    1.35
     opportunities
    1.23
     possibility
    1.20
     wonderful
    1.19
     amazing
    1.19
     možnosti
    1.18
     possibilités
    1.16
     treasures
    1.09
     great
    1.09
    Activations Density 0.047%

    No Known Activations