© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68240
    Prev
    Next
    INDEX
    Explanations

    Category: or Q:

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

    This neuron detects Java (and similar) exception or error type tokens (e.g. Exception names and related syntax).

    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
     État
    -1.09
     tegas
    -1.06
     Système
    -1.05
     ſi
    -1.05
     唯美
    -1.03
    Ứ
    -1.03
     FINANCIAL
    -1.02
     CALIFORN
    -1.01
     ciclismo
    -1.00
    CHOOL
    -0.98
    POSITIVE LOGITS
    ‚¬
    0.97
     eben
    0.91
     Versammlung
    0.90
    左边
    0.87
    вање
    0.87
     綺麗
    0.87
     or
    0.85
    叵
    0.84
    ">(</
    0.83
     '-';
    0.82
    Activations Density 0.000%

    No Known Activations