© 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. 68673
    Prev
    Next
    INDEX
    Explanations

    Listview adapter code

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

    The neuron fires on Java method‐declaration tokens—especially Android ListView/Adapter callbacks—i.e. spotting the return type (View), method name (getView, getChildView), and parameter types (int, ViewGroup, etc.) in method signatures.

    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
     BRUN
    -1.02
    🪛
    -1.02
    CHREIBUNG
    -1.00
     LYON
    -0.98
     its
    -0.98
    cketed
    -0.97
     expédi
    -0.97
     seinem
    -0.96
    фов
    -0.95
    chuhe
    -0.94
    POSITIVE LOGITS
    These
    1.05
    there
    1.02
     These
    1.00
    บาย
    0.99
    そこは
    0.97
     these
    0.96
     There
    0.92
     .
    0.91
    代わり
    0.90
     {},
    0.89
    Activations Density 0.005%

    No Known Activations