© 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. 75024
    Prev
    Next
    INDEX
    Explanations

    privacy policy

    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
    '
    -3.28
     are
    -2.83
    1
    -2.42
     —
    -2.41
    "
    -2.41
    [
    -2.36
     to
    -2.34
     was
    -2.19
     So
    -2.16
    </strong>
    -2.14
    POSITIVE LOGITS
    ᭝
    2.56
    𖡼
    2.52
    vereignty
    2.52
     parachoque
    2.47
     xícara
    2.45
    ेमाल
    2.45
     hır
    2.45
    鯔
    2.44
    ではでは
    2.42
    Наталья
    2.39
    Activations Density 0.005%

    No Known Activations