© 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. 69277
    Prev
    Next
    INDEX
    Explanations

    for example / for instance

    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
     também
    -1.59
     however
    -1.57
     också
    -1.55
     також
    -1.54
     also
    -1.54
     также
    -1.52
     גם
    -1.40
    也是
    -1.38
    も同じ
    -1.35
     również
    -1.34
    POSITIVE LOGITS
     for
    1.75
     if
    1.68
     when
    1.60
     example
    1.46
     podría
    1.44
     например
    1.44
     might
    1.38
     could
    1.38
     may
    1.36
     bijvoorbeeld
    1.27
    Activations Density 0.117%

    No Known Activations