© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65544
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

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

    The neuron spikes on third-person singular present-tense verbs (e.g. “makes”).

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

    No Comments

    Negative Logits
     męskie
    -1.21
     すぎる
    -1.13
     visualización
    -1.09
    cherie
    -1.06
     nikdy
    -1.05
    odyne
    -1.03
     preparada
    -1.02
     artesanía
    -1.02
    rmızı
    -1.02
     reemplazar
    -1.02
    POSITIVE LOGITS
     would
    1.13
    ⇆
    1.12
     perhaps
    0.96
    (/^
    0.96
     incendio
    0.95
     some
    0.93
    iramente
    0.93
     either
    0.92
     maybe
    0.92
    لهم
    0.92
    Activations Density 0.019%

    No Known Activations