© 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. 39785
    Prev
    Next
    INDEX
    Explanations

    sentence ending in punctuation, then start

    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
    otra
    -1.16
    该
    -1.16
     vó
    -1.12
     theyre
    -1.07
    probably
    -1.06
    ᠨ
    -1.03
    itys
    -1.02
    isir
    -1.02
     suelos
    -0.98
     resistente
    -0.97
    POSITIVE LOGITS
     for
    1.63
     in
    1.37
     поэтому
    1.16
     when
    1.08
     from
    1.07
     recently
    1.04
     especially
    1.03
    Among
    1.02
     usually
    1.02
     with
    1.02
    Activations Density 0.139%

    No Known Activations