© 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. 70437
    Prev
    Next
    INDEX
    Explanations

    specific names and entities

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

    The neuron fires strongly on capitalized proper nouns and acronyms (e.g. personal names, organization names, and similar named‐entity 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
    1
    -3.86
    2
    -3.69
    3
    -3.66
    7
    -3.22
    9
    -3.16
    6
    -3.16
    V
    -3.13
    K
    -2.84
    4
    -2.83
    N
    -2.75
    POSITIVE LOGITS
    
    2.70
    derdag
    2.64
    錞
    2.58
    ureusement
    2.53
    我們
    2.47
    皇上
    2.45
    嗵
    2.45
    garh
    2.45
    他们
    2.42
    "--
    2.42
    Activations Density 0.059%

    No Known Activations