© 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. 39563
    Prev
    Next
    INDEX
    Explanations

    built and completed structures

    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
     poszczegól
    -1.23
    Geografía
    -1.16
     each
    -1.15
    HttpEntity
    -1.13
    alucía
    -1.11
    orescence
    -1.09
     LEON
    -1.08
    scienced
    -1.07
     globally
    -1.06
     cuál
    -1.06
    POSITIVE LOGITS
    สร้าง
    1.30
     النبات
    1.27
     built
    1.25
     construction
    1.22
     originally
    1.20
    เกง
    1.16
     by
    1.16
     erected
    1.13
    mí
    1.10
     constructed
    1.09
    Activations Density 0.123%

    No Known Activations