© 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. 10-GEMMASCOPE-RES-131K
    7. 75307
    Prev
    Next
    INDEX
    Explanations

    respective [noun]

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

    This neuron specifically activates on the adjective “respective” (and its exact form).

    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
    <
    -2.89
    ↵↵
    -2.80
    ."
    -2.44
    »
    -2.36
    }$
    -2.36
    }}
    -2.28
    </
    -2.27
    Ꮞ
    -2.23
    }$,
    -2.22
     If
    -2.14
    POSITIVE LOGITS
     burbu
    2.70
    了啊
    2.67
    焌
    2.64
    ⢅
    2.63
    ୌ
    2.48
     nini
    2.45
     guangdong
    2.45
    Награ
    2.44
     daer
    2.38
     uye
    2.33
    Activations Density 0.004%

    No Known Activations