© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27471
    Prev
    Next
    INDEX
    Explanations

    generic, entity, adapter, Radio, Q, Co, //

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

    This neuron activates on generic‐type syntax—specifically the angle‐bracketed type parameters (e.g. “<T>”) and related keywords in code.

    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
    termilk
    -1.22
     Estatal
    -1.12
     lavadora
    -1.11
     warszawa
    -1.09
     gorra
    -1.05
     Theologie
    -1.05
     guantes
    -1.05
     almohada
    -1.04
     perfons
    -1.03
     blusa
    -1.02
    POSITIVE LOGITS
     of
    1.26
    档案馆
    1.04
    erobic
    0.96
     basic
    0.94
    purl
    0.93
     нержа
    0.93
    化为
    0.92
    Actin
    0.91
    ність
    0.90
    glected
    0.90
    Activations Density 0.004%

    No Known Activations