© 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. 111998
    Prev
    Next
    INDEX
    Explanations

    on followed by noun

    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
     will
    -1.58
     her
    -1.46
     who
    -1.41
    whelmed
    -1.38
     ее
    -1.34
    那样
    -1.31
     [
    -1.29
    Frid
    -1.27
    mathrm
    -1.23
     выполня
    -1.23
    POSITIVE LOGITS
     about
    1.95
    </b>
    1.91
     exercí
    1.59
     Muerte
    1.43
     criatura
    1.43
     they
    1.38
    </h4>
    1.38
     ciclista
    1.35
    </sup>
    1.34
     famí
    1.34
    Activations Density 0.107%

    No Known Activations