© 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. 54396
    Prev
    Next
    INDEX
    Explanations

    qualities and characteristics

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

    The neuron detects abstract nouns that express value, status, personal qualities, or social attributes.

    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
     to
    -1.19
    เพื่อ
    -1.19
    setChecked
    -1.02
    ategorie
    -1.01
    ּוֹ
    -0.99
     niektor
    -0.98
    Răsp
    -0.97
    voegd
    -0.94
    əri
    -0.93
    ึกษา
    -0.93
    POSITIVE LOGITS
     that
    0.98
     someone
    0.93
     rayas
    0.92
    狀態
    0.89
     or
    0.89
     indicate
    0.88
    的一种
    0.87
    申し込み
    0.86
     取付
    0.84
    llte
    0.84
    Activations Density 0.061%

    No Known Activations