© 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. 10-GEMMASCOPE-RES-131K
    7. 98682
    Prev
    Next
    INDEX
    Explanations

    up to a point

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

    This neuron detects the discourse marker “Up to the/X point” (e.g. “Up to the immediate present,” “Up to this point”), signaling a boundary or extent.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    {
    -2.36
    .
    -1.88
    the
    -1.48
    \
    -1.34
    m
    -1.33
     But
    -1.32
    L
    -1.30
    }
    -1.25
     lav
    -1.24
    但这
    -1.23
    POSITIVE LOGITS
    ání
    1.66
    %),
    1.65
     esfuer
    1.64
     baskılı
    1.63
    犼
    1.62
     guapos
    1.59
     ersten
    1.55
     նաև
    1.53
     graciosos
    1.52
     ſte
    1.48
    Activations Density 0.026%

    No Known Activations