© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 29159
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns or articles followed by nouns

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

    This neuron does not consistently activate on any particular token or pattern.

    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
     know
    -2.20
    に行く
    -2.00
    geſ
    -1.95
     you
    -1.92
     Перейти
    -1.87
     deudas
    -1.82
     tajem
    -1.81
    био
    -1.80
     advirtió
    -1.79
    andidat
    -1.78
    POSITIVE LOGITS
    ;
    
    2.83
    m
    2.67
    h
    2.53
    n
    2.23
    k
    2.19
    .”
    2.03
    嗵
    2.02
    an
    1.98
    我们
    1.95
    }=
    1.89
    Activations Density 0.006%

    No Known Activations