© 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. 34-GEMMASCOPE-RES-131K
    7. 98075
    Prev
    Next
    INDEX
    Explanations

    sentence endings 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_34/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
     its
    -1.49
     somit
    -1.34
    hline
    -1.24
    其
    -1.23
     }{@
    -1.15
     bamb
    -1.08
     solch
    -1.06
     jedoch
    -1.05
     būt
    -1.05
    writeFieldEnd
    -1.03
    POSITIVE LOGITS
     (
    1.60
     Which
    1.52
    Which
    1.41
     And
    1.39
     ("
    1.33
     I
    1.31
     която
    1.25
     Daß
    1.21
    Ordin
    1.16
     nggak
    1.13
    Activations Density 0.107%

    No Known Activations