© 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. 20171
    Prev
    Next
    INDEX
    Explanations

    days

    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
    AÇÃO
    -1.88
    ίζει
    -1.66
    蘼
    -1.59
     verminder
    -1.55
    "--
    -1.55
    慜
    -1.54
    APER
    -1.52
     numerosos
    -1.50
    咿
    -1.48
     ike
    -1.48
    POSITIVE LOGITS
    -
    2.23
    (
    2.06
     ganze
    1.80
    (\
    1.77
     التي
    1.70
     "..\..\..\
    1.66
    )
    1.66
    at
    1.63
     –
    1.60
     years
    1.59
    Activations Density 0.029%

    No Known Activations