© 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. 10-GEMMASCOPE-RES-131K
    7. 42482
    Prev
    Next
    INDEX
    Explanations

    expressing potential or past actions

    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_10/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
    }$
    -1.71
     it
    -1.67
     but
    -1.54
    をご覧ください
    -1.50
    _{\
    -1.36
    }_{\
    -1.33
    _{
    -1.33
    コチラ
    -1.30
     =
    -1.30
    </b>
    -1.28
    POSITIVE LOGITS
    各种
    1.63
     sebagai
    1.62
     mengangg
    1.55
     menangis
    1.54
    :{
    1.48
    Such
    1.44
     kveld
    1.44
     memeriksa
    1.41
     hänen
    1.40
     tchèque
    1.39
    Activations Density 0.012%

    No Known Activations