© 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. 47368
    Prev
    Next
    INDEX
    Explanations

    cornerstone

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

    The neuron fires on occurrences of “cornerstone” (often split as “corner stones”), i.e. calls out when something is described as a cornerstone.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Kec
    -0.76
    メス
    -0.69
     гори
    -0.69
     implantation
    -0.69
    شک
    -0.69
     mutagenesis
    -0.68
    goed
    -0.66
    nsp
    -0.66
     Permanent
    -0.65
    mace
    -0.65
    POSITIVE LOGITS
    stone
    3.03
     cornerstone
    2.70
     stone
    2.63
    stones
    2.48
    STONE
    2.42
    Stone
    2.39
     corner
    2.33
     Corner
    2.33
     Stone
    2.16
    corner
    2.16
    Activations Density 0.049%

    No Known Activations