© 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. 66324
    Prev
    Next
    INDEX
    Explanations

    satellite and related concepts

    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
     работают
    -2.20
    béco
    -2.11
     ecuator
    -2.08
    手里的
    -2.05
     Comercial
    -2.03
    où
    -1.94
    dersfield
    -1.93
     solida
    -1.92
     Nuestra
    -1.90
     Nuova
    -1.89
    POSITIVE LOGITS
    鋱
    3.17
    }
    3.00
    昞
    2.67
     hinsichtlich
    2.53
    ୌ
    2.50
     unmittelbar
    2.47
     interconnected
    2.45
     impoverished
    2.42
     hauptsächlich
    2.38
     проведен
    2.33
    Activations Density 0.005%

    No Known Activations