© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74432
    Prev
    Next
    INDEX
    Explanations

    Mark Twain, Jagged Alliance, Pennsylvania

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

    The neuron detects fragments of proper names or other named entities (i.e. capitalized name tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     only
    -1.74
    錞
    -1.59
    嫆
    -1.48
     helps
    -1.45
     includes
    -1.44
     latest
    -1.40
     réputation
    -1.38
    هره
    -1.36
     first
    -1.35
     heightened
    -1.34
    POSITIVE LOGITS
    应该
    1.48
     avaient
    1.43
    inafter
    1.42
     Sollte
    1.31
     évek
    1.26
    </i>
    1.23
    necessarily
    1.21
     auraient
    1.21
    </b>
    1.20
     montrent
    1.20
    Activations Density 0.034%

    No Known Activations