© 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. 9768
    Prev
    Next
    INDEX
    Explanations

    sentence endings followed by new statements

    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
     this
    -1.58
     or
    -1.27
     questi
    -1.25
     stund
    -1.16
    “……
    -1.14
    珠宝
    -1.10
     могла
    -1.06
    🎣
    -1.05
     traktor
    -1.05
    perity
    -1.05
    POSITIVE LOGITS
     you
    2.02
     your
    1.85
     ungef
    1.32
     وكان
    1.20
     yours
    1.11
     encontrarás
    1.09
     I
    1.07
     puedes
    1.06
     damals
    1.05
     my
    1.04
    Activations Density 0.021%

    No Known Activations