© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128761
    Prev
    Next
    INDEX
    Explanations

    vulnerable and underserved groups

    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
     on
    -1.23
    ꦏ
    -0.98
    towym
    -0.95
     简介
    -0.93
    댓
    -0.92
     kişinin
    -0.91
     Архивная
    -0.91
    логии
    -0.91
    丨
    -0.90
    転車
    -0.89
    POSITIVE LOGITS
     groups
    1.80
     who
    1.65
    groups
    1.27
     populations
    1.26
     types
    1.24
     subgroups
    1.24
     któ
    1.20
     demographics
    1.20
     group
    1.18
    에게
    1.16
    Activations Density 0.045%

    No Known Activations