© 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. 10-GEMMASCOPE-RES-131K
    7. 72436
    Prev
    Next
    INDEX
    Explanations

    days of the week and dates

    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_10/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
     from
    -2.11
     to
    -2.05
     it
    -2.02
     has
    -2.00
     after
    -1.94
     with
    -1.78
     without
    -1.74
     when
    -1.69
     having
    -1.63
     by
    -1.62
    POSITIVE LOGITS
    鸶
    1.89
    
    1.84
     enorme
    1.77
    苙
    1.75
    　　-
    1.73
     sonre
    1.64
    Investi
    1.63
    Metode
    1.62
    了
    1.62
    </h2>
    1.59
    Activations Density 0.001%

    No Known Activations