© 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. 70648
    Prev
    Next
    INDEX
    Explanations

    case commission institution development engine

    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
     a
    -1.38
     The
    -1.36
     This
    -1.35
     that
    -1.24
     Städten
    -1.16
    weth
    -1.16
     the
    -1.14
     These
    -1.11
     protagonisti
    -1.10
    づけ
    -1.09
    POSITIVE LOGITS
    ↵
    1.43
    Recept
    1.27
     行っ
    1.25
    Suka
    1.23
    Lokasi
    1.22
    Produkt
    1.20
    ільки
    1.20
     ordenado
    1.18
    leč
    1.16
     évidence
    1.16
    Activations Density 0.036%

    No Known Activations