© 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. 93150
    Prev
    Next
    INDEX
    Explanations

    first person statements

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

    This neuron is strongly activated by first-person opinion language, especially uses of “I” and related personal-viewpoint words.

    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
     terkenal
    -1.15
     at
    -1.14
     data
    -1.11
     決定
    -1.05
     business
    -1.05
    了出去
    -1.04
     displayed
    -1.02
     Data
    -1.02
     with
    -1.00
    <?>>
    -0.99
    POSITIVE LOGITS
     malgré
    1.16
     niveaux
    1.08
     médec
    1.08
    новый
    1.07
    魠
    1.05
    ęty
    1.04
     attentes
    1.03
    фы
    1.03
    कार
    1.02
    反而
    1.01
    Activations Density 0.027%

    No Known Activations