© 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. 10-GEMMASCOPE-RES-131K
    7. 12029
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    proper nouns, particularly surnames in legal documents and formal texts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ?”
    -3.31
    ↵↵
    -3.05
    ”-
    -3.02
    </h3>
    -2.88
     ”
    -2.70
     Menschheit
    -2.58
    ”?
    -2.56
    ”)
    -2.53
     Our
    -2.47
    ).”
    -2.41
    POSITIVE LOGITS
    而又
    2.69
    骜
    2.45
     یک
    2.44
    celotti
    2.38
     acús
    2.38
    寕
    2.30
     lomba
    2.28
    ığımız
    2.27
    Kesimpulan
    2.25
    туры
    2.17
    Activations Density 0.021%

    No Known Activations