© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41335
    Prev
    Next
    INDEX
    Explanations

    dish, food, and satellite dishes

    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
    茀
    -2.92
    以上です
    -2.91
    趼
    -2.73
    婠
    -2.72
    ଢ
    -2.70
    目次
    -2.64
    $
    -2.59
    轵
    -2.56
     撮っ
    -2.56
    CONSIN
    -2.56
    POSITIVE LOGITS
    c
    3.00
    g
    2.98
    a
    2.95
    可以
    2.61
    '
    2.45
    2.45
    al
    2.42
    q
    2.39
    ]
    2.39
    m
    2.36
    Activations Density 0.003%

    No Known Activations