© 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. 34-GEMMASCOPE-RES-131K
    7. 98018
    Prev
    Next
    INDEX
    Explanations

    acted deliberately or not

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

    The neuron is triggered by Java method/function names and related keywords (e.g. method declarations like “protected void onActivityResult” and calls like “startActivityForResult”).

    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
    īga
    -0.90
    ښ
    -0.88
    Dim
    -0.82
    ി
    -0.80
     kertoo
    -0.77
    hel
    -0.76
     voidaan
    -0.73
     setEmail
    -0.73
    首先
    -0.73
     Meek
    -0.72
    POSITIVE LOGITS
     on
    3.08
     purpose
    2.92
     On
    2.23
    On
    2.06
    purpose
    2.05
     Purpose
    2.03
     propósito
    1.81
    Purpose
    1.76
     ON
    1.73
     intentional
    1.73
    Activations Density 0.019%

    No Known Activations