© 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. 22-GEMMASCOPE-RES-131K
    7. 64254
    Prev
    Next
    INDEX
    Explanations

    Bayume Mohamed Husen

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

    This neuron selectively fires on tokens that appear in section or article titles (i.e. headings).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     parceiros
    -1.05
     Ministero
    -1.02
     work
    -1.02
    afterEach
    -1.01
    LITERATURE
    -1.01
    do
    -1.01
    武田
    -0.97
    搓
    -0.97
     kilo
    -0.97
     gesti
    -0.97
    POSITIVE LOGITS
     my
    1.36
    Groeten
    1.12
    盈利
    1.09
     koš
    1.09
    grie
    1.08
     casar
    1.07
    inerario
    1.05
    ongeza
    1.05
    ۰۱
    1.04
     Američ
    1.04
    Activations Density 0.026%

    No Known Activations