© 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. 100577
    Prev
    Next
    INDEX
    Explanations

    T- followed by common sequences

    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
    s
    -3.03
    isième
    -2.64
    quelize
    -2.63
    atschappij
    -2.61
     måde
    -2.55
    h
    -2.53
    n
    -2.52
    Mereka
    -2.52
    ława
    -2.47
     für
    -2.45
    POSITIVE LOGITS
    ’
    3.30
     But
    3.06
    \
    2.81
    ?
    2.69
    1
    2.69
     &
    2.63
    ]
    2.59
    źdz
    2.48
     turmoil
    2.47
     でも
    2.47
    Activations Density 0.020%

    No Known Activations