© 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. 43792
    Prev
    Next
    INDEX
    Explanations

    module exports

    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
     jiné
    -1.43
     Envío
    -1.39
     zimní
    -1.37
     innych
    -1.36
     geholfen
    -1.35
     empf
    -1.34
     porcentual
    -1.34
     Imágenes
    -1.30
     oleju
    -1.27
     Cantidad
    -1.27
    POSITIVE LOGITS
     and
    2.53
    </b>
    2.00
     all
    1.44
    ”。
    1.41
    ”？
    1.40
     so
    1.38
    all
    1.29
     are
    1.28
    z
    1.27
    </h4>
    1.26
    Activations Density 0.020%

    No Known Activations