© 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. 73055
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and identifiers

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

    The neuron is activated by semicolon characters (i.e., statement-terminating semicolons 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
     on
    -1.03
     gese
    -1.02
     gangen
    -0.96
     klokken
    -0.96
     balón
    -0.93
    Karakteristik
    -0.92
    旯
    -0.90
     møte
    -0.88
     their
    -0.88
    исто
    -0.84
    POSITIVE LOGITS
     سعد
    0.92
    verschluss
    0.87
    carn
    0.86
    വാ
    0.86
     Schulte
    0.85
    ご覧
    0.85
    ++){
    0.84
    不够
    0.84
    inspiring
    0.84
    adaş
    0.83
    Activations Density 0.000%

    No Known Activations