© 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. 22-GEMMASCOPE-RES-131K
    7. 129643
    Prev
    Next
    INDEX
    Explanations

    regions and geographical areas

    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
    —
    -1.02
    converted
    -0.96
    <bos>
    -0.95
    年生
    -0.94
    ChrTalk
    -0.91
     realizzare
    -0.89
    rinth
    -0.88
    job
    -0.88
     costruire
    -0.87
     snippetHide
    -0.86
    POSITIVE LOGITS
     region
    1.53
     regions
    1.32
     oblasti
    1.10
     mikina
    1.03
    vät
    1.02
     eastern
    1.01
    êt
    1.01
     región
    1.00
    regions
    0.98
    stva
    0.98
    Activations Density 0.074%

    No Known Activations