© 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. 60043
    Prev
    Next
    INDEX
    Explanations

    points where things connect

    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
    鬭
    -3.27
    栳
    -3.08
     ſch
    -2.86
    慙
    -2.86
    쫀
    -2.80
    ᕦ
    -2.72
     یا
    -2.72
    栊
    -2.58
    鱟
    -2.56
     که
    -2.55
    POSITIVE LOGITS
    ]
    3.02
    (
    2.84
     '
    2.78
    はこんな感じ
    2.73
     For
    2.67
     \
    2.41
    d
    2.39
    .
    2.39
    靣
    2.38
     scrutin
    2.31
    Activations Density 0.007%

    No Known Activations