© 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. 10-GEMMASCOPE-RES-131K
    7. 69729
    Prev
    Next
    INDEX
    Explanations

    months of the year

    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
    essero
    -1.66
    </strong>
    -1.63
    ходит
    -1.57
    ("--
    -1.56
    泐
    -1.54
     --
    -1.52
     promove
    -1.48
    
    -1.48
    izzazioni
    -1.48
     ก็
    -1.47
    POSITIVE LOGITS
    b
    1.88
    I
    1.62
    嵛
    1.54
    The
    1.52
     „
    1.52
    )
    1.48
     months
    1.48
    期间
    1.46
    e
    1.43
    ↵
    1.39
    Activations Density 0.022%

    No Known Activations