© 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. 73305
    Prev
    Next
    INDEX
    Explanations

    with [noun phrase] verb-ing

    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
     it
    -1.48
     them
    -1.27
    udades
    -1.23
    ği
    -1.23
    readFileSync
    -1.20
    odziel
    -1.11
    änden
    -1.11
    énu
    -1.10
     will
    -1.09
     not
    -1.08
    POSITIVE LOGITS
    used
    1.28
    Whatever
    1.28
    是她
    1.21
     corriendo
    1.20
    Used
    1.15
     principali
    1.11
    tualmente
    1.11
     веке
    1.10
     て
    1.06
     любой
    1.06
    Activations Density 0.103%

    No Known Activations