© 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. 20607
    Prev
    Next
    INDEX
    Explanations

    neighborhood and district names

    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
    </strong>
    -2.72
    </h3>
    -2.30
    </sub>
    -1.84
    SuspendLayout
    -1.81
    clusão
    -1.80
    痿
    -1.71
    vestres
    -1.71
    </em>
    -1.71
     ſa
    -1.70
    蟳
    -1.70
    POSITIVE LOGITS
    in
    2.14
    1
    1.91
    section
    1.66
     Examining
    1.65
    To
    1.62
     исчез
    1.61
    2
    1.55
     verkau
    1.54
    béco
    1.54
     amable
    1.53
    Activations Density 0.023%

    No Known Activations