© 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. 113459
    Prev
    Next
    INDEX
    Explanations

    collapse of

    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
    牖
    -2.00
    zembro
    -1.95
     zoude
    -1.90
     dezelve
    -1.86
    cised
    -1.81
    蜮
    -1.80
     現貨
    -1.78
     rodrigo
    -1.73
    rdoba
    -1.73
    鶩
    -1.73
    POSITIVE LOGITS
    ↵
    2.19
     With
    2.14
    </
    1.88
    T
    1.78
     llegamos
    1.71
     an
    1.67
     two
    1.64
    ]
    1.62
     με
    1.62
     somos
    1.61
    Activations Density 0.032%

    No Known Activations