© 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. 34-GEMMASCOPE-RES-131K
    7. 91785
    Prev
    Next
    INDEX
    Explanations

    ); and . characters

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

    The neuron fires on UI framework lifecycle/init method identifiers (e.g. viewDidLoad, onCreate, nib, setContentView) 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_34/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
    ritten
    -0.85
     not
    -0.85
    pgp
    -0.83
     Consultado
    -0.82
    enuine
    -0.79
     không
    -0.77
    
    -0.77
    ไม่
    -0.76
     });
    -0.75
    lances
    -0.75
    POSITIVE LOGITS
     endnu
    0.82
     juc
    0.82
     stai
    0.81
    aphthalene
    0.80
    льня
    0.77
    pylene
    0.77
    ews
    0.77
     Utica
    0.77
    اول
    0.76
    unary
    0.76
    Activations Density 0.015%

    No Known Activations