© 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. 65687
    Prev
    Next
    INDEX
    Explanations

    lasso, snare, lass

    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
    锜
    -3.19
    鉝
    -3.06
    瑨
    -2.97
    砹
    -2.91
    sukienka
    -2.91
    脔
    -2.89
    鸶
    -2.80
    铼
    -2.77
    鈁
    -2.67
     محف
    -2.58
    POSITIVE LOGITS
    "
    3.97
    e
    3.02
    as
    2.97
    s
    2.64
     BOTH
    2.44
    ti
    2.44
    ’
    2.42
    ا
    2.41
    ]
    2.38
    5
    2.38
    Activations Density 0.003%

    No Known Activations