© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 129273
    Prev
    Next
    INDEX
    Explanations

    phone numbers, email addresses, contact info

    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
     including
    -1.45
     efficacité
    -1.38
     разных
    -1.32
     této
    -1.30
     aspecto
    -1.27
     включая
    -1.25
     різних
    -1.20
    _
    -1.20
    IFICATIONS
    -1.17
    Berat
    -1.17
    POSITIVE LOGITS
     for
    1.92
    autoIncrement
    1.38
    }.
    1.31
    隳
    1.30
     damaligen
    1.28
    )}.
    1.21
     estekak
    1.19
     their
    1.19
     to
    1.18
     And
    1.18
    Activations Density 0.059%

    No Known Activations