© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13021
    Prev
    Next
    INDEX
    Explanations

    what do I / you

    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
    ครื่อง
    -1.58
    Kullan
    -1.49
     calcetines
    -1.45
    鱨
    -1.43
    cketed
    -1.42
    湏
    -1.41
     ponts
    -1.41
     CELL
    -1.41
    pendentif
    -1.41
     oreilles
    -1.38
    POSITIVE LOGITS
     about
    2.20
     happened
    1.69
     makes
    1.57
     do
    1.54
     does
    1.52
     When
    1.48
     went
    1.48
     happens
    1.47
     has
    1.47
     they
    1.44
    Activations Density 0.038%

    No Known Activations