© 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. 36479
    Prev
    Next
    INDEX
    Explanations

    classification into categories

    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
     respectivos
    -1.01
     and
    -0.97
    Cout
    -0.94
    romole
    -0.91
    Camer
    -0.90
    servant
    -0.88
     einiger
    -0.88
     gewisse
    -0.88
     aantal
    -0.87
    itudine
    -0.87
    POSITIVE LOGITS
    When
    1.25
     when
    1.24
     directly
    1.09
    顾
    1.06
     simply
    1.02
     Guzmán
    1.01
     less
    0.97
    Whatever
    0.96
     berlina
    0.94
    ⏱
    0.94
    Activations Density 0.087%

    No Known Activations