© 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. 48335
    Prev
    Next
    INDEX
    Explanations

    progressive changes

    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
    .
    -3.14
     The
    -3.13
    s
    -2.95
     
    -2.84
     a
    -2.78
     we
    -2.53
     harten
    -2.47
     technisch
    -2.39
     ativar
    -2.39
     his
    -2.33
    POSITIVE LOGITS
    ｘ
    2.72
    During
    2.64
    After
    2.63
    瑧
    2.59
    While
    2.56
    下一篇
    2.53
    적인
    2.50
    Despite
    2.47
    　　「
    2.42
    بسم
    2.42
    Activations Density 0.003%

    No Known Activations