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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70109
    Prev
    Next
    INDEX
    Explanations

    rational use or description

    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
     Of
    -2.52
    翃
    -2.42
     оценка
    -2.34
     nehmen
    -2.22
     нее
    -2.13
     хорошая
    -2.13
     abſ
    -2.08
     установка
    -2.08
    咣
    -2.08
     使っ
    -2.06
    POSITIVE LOGITS
    ’
    3.08
    淠
    2.89
    ൎ
    2.67
     内衣
    2.58
    赑
    2.45
     tijden
    2.45
    м
    2.42
    s
    2.38
    itie
    2.34
    槩
    2.34
    Activations Density 0.003%

    No Known Activations