© 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. 10-GEMMASCOPE-RES-131K
    7. 12469
    Prev
    Next
    INDEX
    Explanations

    geographical locations

    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
     be
    -1.81
    </b>
    -1.70
    ない
    -1.66
     ナビ
    -1.63
    じゃあ
    -1.59
     and
    -1.57
     subray
    -1.53
     wielded
    -1.52
    );
    -1.52
     doccia
    -1.52
    POSITIVE LOGITS
    (
    2.00
    '
    1.98
     rústica
    1.60
    、
    1.52
    的一
    1.49
     remnants
    1.49
    。《
    1.46
    。“
    1.46
     tertawa
    1.46
     Preisen
    1.45
    Activations Density 0.007%

    No Known Activations