© 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. 119430
    Prev
    Next
    INDEX
    Explanations

    pop up or into

    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
    vantaged
    -2.59
    啬
    -2.22
    ми
    -2.20
     to
    -2.16
    蹰
    -2.09
    ی
    -2.08
     have
    -2.08
     Änderungen
    -2.05
     новых
    -2.03
     häufigsten
    -2.02
    POSITIVE LOGITS
    佧
    2.55
    ''
    2.48
    putan
    2.45
    ꜆
    2.39
     использовании
    2.33
     gadis
    2.33
    नलोड
    2.23
    iapkan
    2.22
    a
    2.20
    ଝ
    2.20
    Activations Density 0.012%

    No Known Activations