© 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. 43228
    Prev
    Next
    INDEX
    Explanations

    will be

    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
    leitung
    -2.52
    
    -2.44
     waning
    -2.31
    ↵
    -2.31
    は
    -2.30
     gummy
    -2.23
     demonios
    -2.23
    ⑊
    -2.22
     verdades
    -2.22
     și
    -2.20
    POSITIVE LOGITS
     be
    3.22
    嫫
    2.81
    梘
    2.75
    1
    2.61
    </h2>
    2.31
    people
    2.27
    la
    2.22
    2
    2.16
     People
    2.14
    </td>
    2.11
    Activations Density 0.000%

    No Known Activations