© 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. 74885
    Prev
    Next
    INDEX
    Explanations

    keywords before specific follows

    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
    !(
    -1.45
     its
    -1.45
     their
    -1.41
     both
    -1.30
     get
    -1.23
     all
    -1.20
     regardless
    -1.20
     only
    -1.16
    !』
    -1.14
    !(
    -1.13
    POSITIVE LOGITS
     queste
    1.34
     سات
    1.23
     astfel
    1.21
     asemenea
    1.18
     EIGHT
    1.17
     entomo
    1.17
     Dinas
    1.16
    すっ
    1.14
    えません
    1.14
    IK
    1.14
    Activations Density 0.000%

    No Known Activations