© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26451
    Prev
    Next
    INDEX
    Explanations

    statement termination

    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
     infrastruktur
    -1.24
     obrazu
    -1.23
    蛱
    -1.22
     urat
    -1.22
     trám
    -1.19
    ⏑
    -1.19
    ıda
    -1.18
     靴
    -1.17
    ſſen
    -1.17
    ㈰
    -1.16
    POSITIVE LOGITS
     with
    1.54
     could
    1.42
     may
    1.41
     also
    1.39
     can
    1.34
     their
    1.32
     Maybe
    1.30
     all
    1.29
     this
    1.27
     people
    1.26
    Activations Density 0.009%

    No Known Activations