© 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. 54177
    Prev
    Next
    INDEX
    Explanations

    sentence-ending punctuation following words

    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
     devido
    -1.22
     também
    -1.04
    психо
    -1.02
    んでいる
    -1.00
    куртка
    -1.00
     bougie
    -0.99
    🤱
    -0.98
    ACTO
    -0.98
     reafon
    -0.97
     やすい
    -0.96
    POSITIVE LOGITS
     even
    1.34
     certainly
    1.25
     to
    1.20
     with
    1.20
     may
    1.16
     might
    1.11
     never
    1.07
    ꠥ
    1.04
     probably
    1.02
     triliun
    0.99
    Activations Density 0.025%

    No Known Activations