© 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. 101516
    Prev
    Next
    INDEX
    Explanations

    shiny glitter, glittered things

    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
    毟
    -2.77
    dată
    -2.48
    il
    -2.36
    おきます
    -2.36
     they
    -2.27
     attivo
    -2.25
    曏
    -2.25
     
    -2.23
    ﯿ
    -2.23
    ar
    -2.22
    POSITIVE LOGITS
    .
    2.81
    ,"
    2.48
    ]
    2.47
    }
    2.17
     prise
    2.17
     insulating
    2.16
    ubahan
    2.09
    </h3>
    2.06
    ࿆
    2.05
    色の
    2.03
    Activations Density 0.002%

    No Known Activations