© 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. 34-GEMMASCOPE-RES-131K
    7. 87243
    Prev
    Next
    INDEX
    Explanations

    place names and company names

    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_34/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
     cómoda
    -1.37
     indicado
    -1.27
    黑衣
    -1.26
    さんから
    -1.20
    さんへ
    -1.18
     estadounidense
    -1.18
    をしていた
    -1.17
    の方に
    -1.16
    ﱠ
    -1.16
     animado
    -1.15
    POSITIVE LOGITS
    ฯ
    2.14
    LAHOMA
    1.15
     dicendo
    1.08
    gio
    1.08
    flex
    1.06
    ⤒
    1.03
    ha
    1.02
    hd
    1.02
    🤘
    1.02
    and
    1.01
    Activations Density 0.132%

    No Known Activations