© 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. 105376
    Prev
    Next
    INDEX
    Explanations

    no such thing as

    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
    蛲
    -2.27
    𖧵
    -2.20
    蚰
    -2.14
    fficients
    -2.13
    艄
    -2.09
    蹑
    -2.06
    鉏
    -2.05
    玊
    -1.98
     korban
    -1.96
    で見る
    -1.96
    POSITIVE LOGITS
    .”
    2.66
    ]
    1.90
     to
    1.90
     Bewußt
    1.88
    like
    1.88
    ’
    1.87
    :
    1.84
     einzigartigen
    1.80
     a
    1.77
    但是
    1.77
    Activations Density 0.008%

    No Known Activations