© 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. 130856
    Prev
    Next
    INDEX
    Explanations

    numbers and prices

    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
     célè
    -1.22
     ressemb
    -1.13
     ſon
    -1.10
     horaire
    -1.09
     frança
    -1.09
     theſe
    -1.07
     réfrig
    -1.06
    鶿
    -1.06
     rése
    -1.05
    킁
    -1.05
    POSITIVE LOGITS
     if
    2.66
     for
    2.00
     with
    1.64
     If
    1.55
     in
    1.52
     если
    1.39
     depending
    1.35
     when
    1.34
     jika
    1.21
     With
    1.20
    Activations Density 0.036%

    No Known Activations