© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67407
    Prev
    Next
    INDEX
    Explanations

    hypertensive, underrated, power play, content marketing, surprising, European countries, critical controls, surface detail, South African, activist, surefire

    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
    ’
    -2.69
     to
    -2.23
    )
    -2.05
     if
    -1.95
    ^{\
    -1.88
     "..\..\
    -1.74
     "..\..\..\
    -1.73
    quelize
    -1.73
    henswürdigkeiten
    -1.71
    </th>
    -1.69
    POSITIVE LOGITS
     maravill
    1.97
    </h2>
    1.76
     impresionantes
    1.73
     literaria
    1.70
    明显的
    1.66
     edificios
    1.66
    "-
    1.64
     helados
    1.63
     proveniente
    1.63
    非常的
    1.63
    Activations Density 0.198%

    No Known Activations