© 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. 66961
    Prev
    Next
    INDEX
    Explanations

    describing purpose after "in"

    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
     for
    -2.47
    :
    -2.20
     on
    -2.20
     an
    -2.05
     as
    -1.80
     December
    -1.80
     October
    -1.78
     only
    -1.70
     Vordergrund
    -1.70
     September
    -1.70
    POSITIVE LOGITS
    </strong>
    2.61
    螃
    2.27
    苼
    2.16
     verhind
    2.05
     -"
    1.97
    夘
    1.96
    Ꮉ
    1.91
    k
    1.88
    n
    1.87
    읭
    1.85
    Activations Density 0.012%

    No Known Activations