© 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. 71939
    Prev
    Next
    INDEX
    Explanations

    code suffixes, defines, and abbreviations

    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
     and
    -1.95
    ],
    -1.87
    ’,
    -1.75
    」、「
    -1.64
     other
    -1.64
    },
    -1.61
     cannot
    -1.58
     analisis
    -1.58
     BRASIL
    -1.55
     this
    -1.51
    POSITIVE LOGITS
    了很多
    1.74
    了不少
    1.73
    erobic
    1.70
    omal
    1.63
    ཥ
    1.62
     diferencias
    1.60
    tismo
    1.58
     '
    1.55
    та
    1.54
    𝗡
    1.54
    Activations Density 0.034%

    No Known Activations