© 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. 47521
    Prev
    Next
    INDEX
    Explanations

    HTML tags and code delimiters

    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
    1
    -2.53
    Даже
    -2.36
    7
    -2.16
    䉴
    -2.16
    2
    -2.16
    The
    -2.14
    Чтобы
    -2.09
    尤其
    -2.08
     Even
    -2.08
    Even
    -2.05
    POSITIVE LOGITS
    簠
    2.55
     to
    2.52
    齜
    2.41
     柜
    2.34
     нашим
    2.23
     представители
    2.13
    葑
    2.06
     seite
    2.05
    bagno
    2.03
    ⢫
    2.03
    Activations Density 0.000%

    No Known Activations