© 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. 103204
    Prev
    Next
    INDEX
    Explanations

    Roman numeral II

    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
    荩
    -2.59
     They
    -2.36
    一个
    -2.31
     เพราะ
    -2.30
    ↵↵
    -2.30
    ないけど
    -2.28
    她
    -2.27
    は
    -2.25
     are
    -2.17
    0
    -2.14
    POSITIVE LOGITS
    琲
    2.89
    鹛
    2.80
    鼷
    2.69
    Ꮚ
    2.53
     auffi
    2.47
    鶿
    2.45
    𓋼
    2.44
     ſch
    2.44
    鬭
    2.42
    崃
    2.39
    Activations Density 0.019%

    No Known Activations