© 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. 12965
    Prev
    Next
    INDEX
    Explanations

    seeing myself and others

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

    The neuron strongly activates on subordinating adverbial connectors—especially “when” (and similar words like “especially”) that introduce clauses.

    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
    可能会
    -0.99
    abytes
    -0.96
     according
    -0.92
    漲
    -0.92
     granul
    -0.91
    LIK
    -0.90
    )>>
    -0.88
    сить
    -0.86
    likely
    -0.86
     meest
    -0.85
    POSITIVE LOGITS
     when
    1.31
     that
    1.28
     fábricas
    1.26
     cuando
    1.22
     people
    1.21
    When
    1.20
    Sometimes
    1.18
     my
    1.16
     doká
    1.13
     мне
    1.12
    Activations Density 0.050%

    No Known Activations