© 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. 65975
    Prev
    Next
    INDEX
    Explanations

    discount retail and company names

    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
     as
    -1.54
     this
    -1.54
    p
    -1.51
     ataupun
    -1.44
     with
    -1.42
    縹
    -1.41
    T
    -1.41
     unhappy
    -1.41
    en
    -1.38
     Definitely
    -1.38
    POSITIVE LOGITS
     Aldi
    1.80
    dientemente
    1.73
     ১
    1.65
    aksi
    1.55
     واقع
    1.48
     améli
    1.46
    కర్య
    1.46
     tp
    1.46
    鸯
    1.43
    ᚔ
    1.41
    Activations Density 0.002%

    No Known Activations