© 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. 14995
    Prev
    Next
    INDEX
    Explanations

    initials followed by period

    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
     now
    -2.13
     tentativo
    -1.75
    meteries
    -1.70
     terzo
    -1.59
     suono
    -1.57
    ┿
    -1.55
     ஒரு
    -1.52
     espírito
    -1.51
     blocco
    -1.50
     commento
    -1.46
    POSITIVE LOGITS
    f
    1.91
    v
    1.90
    l
    1.80
    n
    1.74
    c
    1.69
    ti
    1.66
    as
    1.66
    k
    1.66
    }
    1.60
    ene
    1.59
    Activations Density 0.008%

    No Known Activations