© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56853
    Prev
    Next
    INDEX
    Explanations

    describing state or similarity

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

    The neuron detects copular “be” verbs (is/are/was) in descriptive or definitional predicate constructions.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    װ
    -1.08
    ̙
    -0.96
    řit
    -0.95
     sentí
    -0.94
    fälle
    -0.94
    這
    -0.93
     nabíd
    -0.93
     весело
    -0.93
    cidas
    -0.91
    ’
    -0.91
    POSITIVE LOGITS
     similar
    1.76
     conducive
    1.46
     changed
    1.46
     what
    1.43
     identical
    1.42
     such
    1.41
     unchanged
    1.26
     akin
    1.22
     quella
    1.20
     that
    1.13
    Activations Density 0.108%

    No Known Activations