© 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. 47625
    Prev
    Next
    INDEX
    Explanations

    Caleb, Kosovo, crawler, votes

    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
    ’
    -2.88
     participado
    -2.38
    ↵
    -2.31
     entrado
    -2.31
     erneu
    -2.27
    '
    -2.14
    ]
    -2.09
    il
    -2.09
     permitido
    -2.03
    {
    -2.02
    POSITIVE LOGITS
    ндарт
    3.00
    炱
    2.98
     إذا
    2.67
     redaktion
    2.64
    钐
    2.58
    ﮩ
    2.55
    ᷆
    2.53
    欷
    2.50
    嫆
    2.50
     sexuelle
    2.50
    Activations Density 0.002%

    No Known Activations