© 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. 98913
    Prev
    Next
    INDEX
    Explanations

    ink fluid, ribbon, jet

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

    The neuron responds when the text names ink or similar printing/pigment materials (e.g. “ink,” “pigment,” “toner”)

    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
     in
    -1.55
     huellas
    -1.46
     my
    -1.46
     no
    -1.42
     wide
    -1.40
     dimension
    -1.40
     dieses
    -1.35
    in
    -1.34
     hiding
    -1.34
     drugie
    -1.34
    POSITIVE LOGITS
    Ṅ
    1.71
     Luar
    1.47
     realtime
    1.45
     Atención
    1.40
     metropolitana
    1.38
    ري
    1.35
    י
    1.35
    他們
    1.34
     menjalani
    1.32
     Estar
    1.30
    Activations Density 0.278%

    No Known Activations