© 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. 22-GEMMASCOPE-RES-131K
    7. 95625
    Prev
    Next
    INDEX
    Explanations

    power supply

    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_22/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
     generell
    -1.79
    without
    -1.76
    ⮑
    -1.75
    ཿ
    -1.75
     boister
    -1.73
    actéristi
    -1.73
    ᕮ
    -1.68
     ludicrous
    -1.66
    ྄
    -1.63
     quintessential
    -1.59
    POSITIVE LOGITS
     only
    1.88
     one
    1.69
     Though
    1.66
     if
    1.59
     Although
    1.53
     Almost
    1.52
     nine
    1.51
     putting
    1.50
     when
    1.49
     February
    1.49
    Activations Density 0.222%

    No Known Activations