© 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. 10787
    Prev
    Next
    INDEX
    Explanations

    guy or stuff

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

    The neuron strongly activates on informal, generic nouns or placeholders (like “guy,” “guys,” “stuff,” “kind”) that refer to people or things in a colloquial way.

    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
    9
    -1.84
    3
    -1.76
    4
    -1.65
    8
    -1.53
    5
    -1.39
     =
    -1.36
    ’
    -1.36
     bekannten
    -1.31
    你怎么
    -1.30
    你别
    -1.30
    POSITIVE LOGITS
    푅
    1.51
    鍇
    1.48
    鮃
    1.45
    𖣘
    1.45
    और
    1.39
     chilen
    1.35
    🪐
    1.35
    owulf
    1.35
    Ꮇ
    1.35
    ⾦
    1.34
    Activations Density 0.120%

    No Known Activations