© 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. 69268
    Prev
    Next
    INDEX
    Explanations

    technology and systems

    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
     if
    -1.60
     for
    -1.52
    に行きました
    -1.46
     when
    -1.45
     jika
    -1.38
     können
    -1.38
     веке
    -1.36
    に行ってきました
    -1.35
     If
    -1.34
    mapTo
    -1.33
    POSITIVE LOGITS
    issime
    1.33
     garcia
    1.30
     procédé
    1.28
     ™
    1.27
    ™
    1.23
     berger
    1.21
     archi
    1.20
     burch
    1.20
     favoriser
    1.20
     citroen
    1.20
    Activations Density 0.038%

    No Known Activations