© 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. 54279
    Prev
    Next
    INDEX
    Explanations

    URLs and foreign text

    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
    bow
    -1.19
     it
    -1.19
     decât
    -1.17
    ABAD
    -1.13
    kward
    -1.13
    )]{
    -1.11
    bergement
    -1.08
    ₃
    -1.07
     puțin
    -1.07
     které
    -1.07
    POSITIVE LOGITS
     benzin
    1.27
    了过来
    1.16
     grotte
    1.12
     ((((
    1.12
     Belgien
    1.05
    腟
    1.05
    renault
    1.03
     prachtig
    1.02
     panneau
    1.02
     (\%)
    1.02
    Activations Density 0.011%

    No Known Activations