© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4997
    Prev
    Next
    INDEX
    Explanations

    US dollar amounts

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

    The neuron flags boilerplate or metadata tokens—words and punctuation that tend to appear in template sections (like “This entry was posted,” “filed,” “under,” section‐headers, the period ending a block, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ২
    0.83
    CHE
    0.80
     группа
    0.77
     کہ
    0.76
    Qaeda
    0.75
    ankar
    0.75
    ０
    0.75
    喈
    0.75
    𐰃
    0.74
     иннова
    0.74
    POSITIVE LOGITS
     plats
    0.86
    <h5>
    0.85
     Cozy
    0.84
     Elevator
    0.84
     Abandon
    0.82
    <h4>
    0.78
     philipp
    0.77
     slog
    0.74
     Ready
    0.74
     Badger
    0.74
    Activations Density 0.000%

    No Known Activations