© 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. 71989
    Prev
    Next
    INDEX
    Explanations

    code delimiters and keywords

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

    The neuron detects conditional‐test syntax—e.g. the comparison or logical operators and enclosing parentheses used in if-statements and preprocessor conditionals.

    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
    EMIA
    -1.00
     kombiniert
    -0.92
     deaktivi
    -0.91
    сов
    -0.91
     kümmern
    -0.90
    IVERY
    -0.89
    ERN
    -0.86
    Ẻ
    -0.84
     franca
    -0.84
    
    -0.82
    POSITIVE LOGITS
     политика
    0.89
    Entonces
    0.87
    Chara
    0.85
    Advert
    0.83
    —¿
    0.83
    lectable
    0.83
    Telefax
    0.83
    Photoshop
    0.82
    Australie
    0.81
    سع
    0.81
    Activations Density 0.005%

    No Known Activations