© 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. 11861
    Prev
    Next
    INDEX
    Explanations

    what is/was

    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
     and
    -2.53
     of
    -2.20
     or
    -1.98
    इटम
    -1.84
     to
    -1.80
    低于
    -1.77
     "
    -1.70
     beweging
    -1.67
     tegens
    -1.65
     Duitsland
    -1.55
    POSITIVE LOGITS
    ônia
    1.86
     стоковая
    1.83
    樒
    1.76
    IGRATION
    1.73
    图片来源
    1.72
     traditionnels
    1.70
     mauva
    1.70
    ◩
    1.70
     cortina
    1.68
    图源
    1.66
    Activations Density 0.030%

    No Known Activations