© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34800
    Prev
    Next
    INDEX
    Explanations

    sentence endings

    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
    кож
    -1.28
     révé
    -1.26
     sés
    -1.22
    蚰
    -1.22
     également
    -1.19
     känns
    -1.19
     courant
    -1.17
    ครื่อง
    -1.16
    rester
    -1.16
     även
    -1.16
    POSITIVE LOGITS
     what
    2.20
     this
    2.03
     it
    1.88
     our
    1.83
     that
    1.78
     only
    1.72
     when
    1.63
     so
    1.60
     through
    1.58
     thus
    1.52
    Activations Density 0.035%

    No Known Activations