© 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. 22-GEMMASCOPE-RES-131K
    7. 9393
    Prev
    Next
    INDEX
    Explanations

    dollars, parentheses, brackets

    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_22/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
    名前
    -1.10
    have
    -1.06
    ቪ
    -1.01
    因为
    -1.01
     myriad
    -1.01
     ざ
    -1.00
    近年
    -0.99
     Songtext
    -0.99
     kapital
    -0.98
     kontin
    -0.98
    POSITIVE LOGITS
     for
    1.34
     in
    1.28
    の方も
    1.23
     from
    1.20
     сър
    1.16
     también
    1.11
     here
    1.09
    唖
    1.09
     стъ
    1.08
    ⾦
    1.07
    Activations Density 0.051%

    No Known Activations