© 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. 42920
    Prev
    Next
    INDEX
    Explanations

    space or spaces

    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
    </h2>
    -2.16
     verminder
    -1.86
     scherm
    -1.84
    桕
    -1.78
    鲎
    -1.76
    巂
    -1.73
    垸
    -1.65
    тельным
    -1.63
     empezar
    -1.63
    тися
    -1.61
    POSITIVE LOGITS
    -
    2.20
    "
    2.02
    e
    2.02
    /
    1.98
    y
    1.91
    0
    1.84
     زیادی
    1.81
    c
    1.80
    but
    1.79
    ↵↵↵
    1.78
    Activations Density 0.051%

    No Known Activations