© 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. 111675
    Prev
    Next
    INDEX
    Explanations

    Canadian domains

    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
     decidi
    -2.56
    ghalaya
    -2.53
    寕
    -2.47
    quelize
    -2.45
     exercí
    -2.45
     думал
    -2.44
    RemindMe
    -2.41
     imprimi
    -2.39
     retira
    -2.38
     стоковая
    -2.38
    POSITIVE LOGITS
    )
    2.72
    ?
    2.41
    &
    2.38
    of
    2.38
     &
    2.38
    *
    2.33
     my
    2.31
    された
    2.28
     has
    2.23
    "
    2.23
    Activations Density 0.002%

    No Known Activations