© 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. 22-GEMMASCOPE-RES-131K
    7. 15964
    Prev
    Next
    INDEX
    Explanations

    past records, history, and logs

    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
    glove
    -0.98
     już
    -0.96
    долго
    -0.95
    lateinit
    -0.93
     предвари
    -0.90
    циали
    -0.88
     Neben
    -0.88
    garmin
    -0.87
     мем
    -0.86
     político
    -0.86
    POSITIVE LOGITS
     history
    1.70
     histories
    1.36
     records
    1.30
     recent
    1.28
     record
    1.25
     past
    1.25
     histori
    1.19
     история
    1.16
    记录
    1.14
    history
    1.13
    Activations Density 0.049%

    No Known Activations