© 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. 34-GEMMASCOPE-RES-131K
    7. 91086
    Prev
    Next
    INDEX
    Explanations

    list, math, programming, science

    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_34/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
    InputBorder
    -1.15
     ideen
    -1.14
    Ǿ
    -1.09
     theſe
    -1.06
    OGRAPH
    -1.03
     sembla
    -1.01
     خواهد
    -1.01
     klima
    -1.00
    𐐀
    -0.99
     डाउनलोड
    -0.97
    POSITIVE LOGITS
    焄
    1.13
     деву
    1.03
    kubernetes
    1.03
     historical
    1.03
     sustancias
    1.02
     pagare
    1.01
     بالإضافة
    1.00
    枚目
    1.00
    必定
    0.98
     majority
    0.98
    Activations Density 0.003%

    No Known Activations