© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65908
    Prev
    Next
    INDEX
    Explanations

    quantifiers like both, several, all, numerous, various, any

    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
     on
    -2.13
     during
    -1.71
     their
    -1.70
     these
    -1.65
     its
    -1.63
     Surprisingly
    -1.61
     regarding
    -1.60
     this
    -1.59
    Surprisingly
    -1.58
     only
    -1.56
    POSITIVE LOGITS
    憷
    1.97
    for
    1.73
     другие
    1.55
    齶
    1.39
    獓
    1.36
     beſ
    1.36
    Shown
    1.34
    饜
    1.34
     shown
    1.33
     identif
    1.33
    Activations Density 0.077%

    No Known Activations