© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54114
    Prev
    Next
    INDEX
    Explanations

    question marks and modal verbs

    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
     diing
    -1.50
     kering
    -1.18
     propiet
    -1.18
     Conclu
    -1.14
     libere
    -1.14
     estadounid
    -1.12
     coffret
    -1.12
     ワゴン
    -1.11
     femen
    -1.11
     Administr
    -1.10
    POSITIVE LOGITS
     and
    1.88
     And
    1.80
     or
    1.51
     But
    1.39
     It
    1.30
     Or
    1.28
     They
    1.24
     Also
    1.24
     Then
    1.22
     permitiendo
    1.20
    Activations Density 0.030%

    No Known Activations