© 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. 119053
    Prev
    Next
    INDEX
    Explanations

    BY [G. A.]

    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
    eſ
    -2.34
     花纹
    -2.33
     systé
    -2.22
    蟥
    -2.20
    瘊
    -2.17
    皤
    -2.16
    鼍
    -2.13
     mortos
    -2.09
    蜮
    -2.09
     搞笑
    -2.06
    POSITIVE LOGITS
    Just
    2.31
    ↵↵
    2.30
    Even
    2.19
    When
    2.17
    Very
    2.09
    After
    2.08
    Two
    2.06
    We
    2.06
    All
    2.05
     in
    2.02
    Activations Density 0.004%

    No Known Activations