© 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. 103201
    Prev
    Next
    INDEX
    Explanations

    ata

    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
    a
    -2.94
    r
    -2.63
    ा
    -2.47
    can
    -2.44
    怍
    -2.38
    }$
    -2.34
    vantaged
    -2.30
    could
    -2.27
    m
    -2.27
    no
    -2.25
    POSITIVE LOGITS
    ata
    3.44
     intensive
    2.55
    dė
    2.48
     inescapable
    2.47
     emphatic
    2.45
     extremes
    2.41
     unwavering
    2.39
     unimaginable
    2.34
     empathetic
    2.33
     impede
    2.31
    Activations Density 0.008%

    No Known Activations