© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 129633
    Prev
    Next
    INDEX
    Explanations

    such followed by adjective

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

    The neuron specifically detects the emphatic intensifier “such.”

    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
     of
    -3.16
     to
    -2.98
    at
    -2.28
     is
    -2.23
     you
    -2.05
    to
    -2.03
    ad
    -2.02
    our
    -1.98
    on
    -1.98
    le
    -1.96
    POSITIVE LOGITS
     csak
    1.89
    続いて
    1.79
    )&&(
    1.75
    yskland
    1.70
    });*/
    1.70
    sumoto
    1.67
    写真は
    1.66
    叕
    1.66
     cabezas
    1.64
    )):
    
    1.63
    Activations Density 0.011%

    No Known Activations