© 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. 104389
    Prev
    Next
    INDEX
    Explanations

    function declarations and definitions

    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
     toujours
    -1.30
    gunakan
    -1.27
     sobot
    -1.25
     nadru
    -1.23
     sklep
    -1.20
    ᯾
    -1.19
     koneksi
    -1.18
     spokoj
    -1.18
     nowy
    -1.16
     osz
    -1.16
    POSITIVE LOGITS
     after
    1.22
     different
    1.19
     during
    1.17
    on
    1.15
    di
    1.07
    at
    1.06
     numerous
    1.05
     partly
    1.02
     when
    1.02
    which
    1.02
    Activations Density 0.004%

    No Known Activations