© 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. 90744
    Prev
    Next
    INDEX
    Explanations

    funding amounts

    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
    Instead
    -1.95
    It
    -1.84
    These
    -1.78
     vaksin
    -1.73
    Again
    -1.53
    Its
    -1.53
     borsa
    -1.53
    这些
    -1.51
    這些
    -1.46
     It
    -1.45
    POSITIVE LOGITS
     from
    1.56
    randir
    1.51
    入る
    1.50
    /}.
    1.44
    楽しめます
    1.43
     vermogen
    1.41
    Ȩ
    1.41
    vají
    1.41
    随即
    1.40
    缥
    1.39
    Activations Density 0.184%

    No Known Activations