© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78240
    Prev
    Next
    INDEX
    Explanations

    action and date

    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
     tages
    -1.12
     Kopi
    -1.10
     artig
    -1.05
     berge
    -1.04
     visse
    -1.03
     regionale
    -1.02
     reisen
    -1.02
     mentale
    -1.01
     FACEBOOK
    -1.01
    pekte
    -1.00
    POSITIVE LOGITS
     time
    2.83
     date
    2.72
    Date
    1.98
     Date
    1.95
     dates
    1.77
    date
    1.73
    DATE
    1.59
     method
    1.58
     type
    1.49
    DateTime
    1.46
    Activations Density 0.028%

    No Known Activations