© 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. 42684
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
    1
    -4.25
    4
    -3.36
    6
    -3.22
    5
    -3.08
     haupts
    -3.03
    9
    -2.88
    2
    -2.80
     ausser
    -2.80
     frattempo
    -2.75
    7
    -2.75
    POSITIVE LOGITS
    '
    2.75
     (!)
    2.31
    (!)
    2.28
    🔸
    2.23
    说起
    2.22
     exquisitely
    2.14
     multifaceted
    2.14
     There
    2.13
    图片来源
    2.11
    伦敦
    2.11
    Activations Density 0.039%

    No Known Activations