© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10846
    Prev
    Next
    INDEX
    Explanations

    special characters and abbreviations

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

    the presence of unusually long, content‐bearing tokens (e.g. multi-syllabic words)

    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_31_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
     "./
    0.72
     mdl
    0.69
     rangle
    0.69
     ":
    0.68
    ing
    0.67
     lessor
    0.67
     wrongly
    0.64
     “
    0.63
     omn
    0.63
     PDF
    0.63
    POSITIVE LOGITS
    هر
    0.85
    Jumlah
    0.73
    ഹി
    0.73
    ĸ
    0.73
    Flipper
    0.73
    א
    0.73
    რულ
    0.72
    ود
    0.72
    Rib
    0.72
    Historia
    0.72
    Activations Density 0.000%

    No Known Activations