© 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. 34-GEMMASCOPE-RES-131K
    7. 65034
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
     utterly
    -0.94
     obviously
    -0.90
     ironically
    -0.89
     despite
    -0.89
    väll
    -0.88
     ostensibly
    -0.85
     khổ
    -0.85
     impressive
    -0.84
     started
    -0.84
     having
    -0.84
    POSITIVE LOGITS
     verbunden
    0.88
     regresó
    0.85
    rativo
    0.85
    喜爱
    0.82
     उस
    0.82
     geleg
    0.80
    berries
    0.79
     molti
    0.78
    tet
    0.78
    现
    0.78
    Activations Density 0.023%

    No Known Activations