© 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. 123791
    Prev
    Next
    INDEX
    Explanations

    what, which, who followed by verbs

    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
    -2.08
    5
    -1.92
    6
    -1.88
    7
    -1.82
    4
    -1.82
    1
    -1.70
     diseñadores
    -1.70
     Tätigkeit
    -1.68
     nếu
    -1.61
    0
    -1.59
    POSITIVE LOGITS
    s
    1.82
    ar
    1.77
    ans
    1.59
     who
    1.56
    ógico
    1.46
    ing
    1.46
    zygous
    1.46
    ⁃
    1.44
     is
    1.41
    浮现
    1.41
    Activations Density 0.005%

    No Known Activations