© 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. 71636
    Prev
    Next
    INDEX
    Explanations

    various entities and associated concepts

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

    This neuron detects sentences or headings where a subject is introduced or defined—i.e. occurrences of “The X is/are…” or similar lead‐in descriptions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     kalend
    -1.02
    lanan
    -1.00
    रु
    -0.98
     but
    -0.94
    してる
    -0.92
    韓國
    -0.91
     two
    -0.90
     mochilas
    -0.89
     misiones
    -0.88
     gefüllt
    -0.86
    POSITIVE LOGITS
    これで
    1.05
     przecież
    1.05
    就能
    1.05
    从此
    1.05
     normally
    1.02
     will
    1.02
     теперь
    1.00
     often
    1.00
     attraverso
    0.99
    也能
    0.99
    Activations Density 0.096%

    No Known Activations