© 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. 68686
    Prev
    Next
    INDEX
    Explanations

    HTML tag attributes

    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
     an
    -1.38
     but
    -1.27
     Beziehungen
    -1.23
    nī
    -1.21
     getting
    -1.20
     that
    -1.18
    ！(
    -1.18
     on
    -1.18
     and
    -1.16
     trying
    -1.16
    POSITIVE LOGITS
     Atención
    1.48
     Dinas
    1.35
     forment
    1.30
     perche
    1.26
     Ministre
    1.24
     unbelievably
    1.24
     innumer
    1.23
     dilapidated
    1.22
     EVEN
    1.20
     निम्नलिखित
    1.20
    Activations Density 0.014%

    No Known Activations