© 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. 103155
    Prev
    Next
    INDEX
    Explanations

    names followed by words or punctuation

    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
    доступ
    -1.41
     Both
    -1.34
    ógica
    -1.34
     cómoda
    -1.33
     всѣ
    -1.32
    ními
    -1.30
    使用了
    -1.27
    bershka
    -1.27
     لكن
    -1.27
    acakt
    -1.27
    POSITIVE LOGITS
     –
    1.61
    8
    1.55
    7
    1.51
     problemet
    1.45
    ne
    1.45
    n
    1.43
    9
    1.41
    6
    1.31
     --
    1.31
    In
    1.31
    Activations Density 0.217%

    No Known Activations