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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68172
    Prev
    Next
    INDEX
    Explanations

    shell script, Q&A, code snippets

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

    The neuron fires on Java annotation and framework API class names (e.g. RequestMapping, Path, Entity, ColumnInfo, ConfigurationProperties).

    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
    IBLIO
    -1.05
     TECHNOLOGIES
    -1.05
    ltä
    -1.00
    rash
    -0.98
     doulou
    -0.97
     Medications
    -0.96
     Chrift
    -0.95
    莛
    -0.95
    一点点
    -0.94
    voerd
    -0.93
    POSITIVE LOGITS
     and
    1.17
     from
    1.09
     especially
    0.90
     like
    0.90
    when
    0.87
    From
    0.85
     on
    0.85
     for
    0.84
     as
    0.82
    وى
    0.81
    Activations Density 0.000%

    No Known Activations