© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98893
    Prev
    Next
    INDEX
    Explanations

    64-bit operating systems and hardware

    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
    Negative Logits
     ciertos
    -1.76
    Ꮅ
    -1.57
     rappeler
    -1.54
     Pristup
    -1.54
    羕
    -1.52
    囘
    -1.47
     complementa
    -1.46
    大多
    -1.45
     pries
    -1.45
     largely
    -1.44
    POSITIVE LOGITS
     её
    1.50
     और
    1.45
    ")
    1.41
     участи
    1.35
    with
    1.34
    )$
    1.33
    ”，
    1.32
    )$,
    1.32
     feels
    1.31
     Mental
    1.30
    Activations Density 0.022%

    No Known Activations