© 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. 34-GEMMASCOPE-RES-131K
    7. 75765
    Prev
    Next
    INDEX
    Explanations

    description of prior art

    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_34/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
    vably
    -0.79
     között
    -0.79
     atendimento
    -0.78
    sterne
    -0.78
    ⓢ
    -0.78
     APPELLANT
    -0.75
     quei
    -0.75
    لبية
    -0.75
     representan
    -0.74
     имеются
    -0.74
    POSITIVE LOGITS
     contents
    1.33
     characteristics
    1.30
     size
    1.25
     of
    1.22
     length
    1.16
     width
    1.13
     strength
    1.10
     nameof
    1.10
    性质
    1.09
     thickness
    1.08
    Activations Density 0.344%

    No Known Activations