© 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. 79480
    Prev
    Next
    INDEX
    Explanations

    names starting with Daniel

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

    The neuron fires on tokens that are fragments of surnames immediately following the given name “Daniel,” i.e. the last‐name portion of “Daniel X” name sequences.

    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
    textrm
    -0.99
     crafts
    -0.87
    masan
    -0.81
    ět
    -0.81
     aikana
    -0.77
     simpan
    -0.76
     disciplines
    -0.76
     delicacy
    -0.74
     accomplishment
    -0.73
     abbreviation
    -0.73
    POSITIVE LOGITS
     daniel
    0.83
     στιγ
    0.78
    iction
    0.77
    ística
    0.76
     देखें
    0.76
    انون
    0.73
    =[]
    0.72
    "))
    0.72
     Rosary
    0.72
     assim
    0.71
    Activations Density 0.032%

    No Known Activations