© 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. 42968
    Prev
    Next
    INDEX
    Explanations

    place names and geographical features

    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
     "
    -2.66
    -
    -2.47
     kolejne
    -2.44
    闆
    -2.42
    釙
    -2.41
     当
    -2.39
    皷
    -2.33
     貨
    -2.31
    まき
    -2.28
     あります
    -2.22
    POSITIVE LOGITS
    。“
    3.06
    摃
    2.92
    趼
    2.69
    ,“
    2.66
    they
    2.61
    “
    2.59
    ஂ
    2.52
    ｍ
    2.36
    媄
    2.36
    you
    2.34
    Activations Density 0.081%

    No Known Activations