© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98314
    Prev
    Next
    INDEX
    Explanations

    highest, rose, Hardy, Preliminary, Barnaby

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

    The neuron reliably lights up on numeric data—numbers and related statistical figures in text.

    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
     indios
    -1.06
     three
    -1.04
     several
    -1.02
    много
    -1.02
     phénom
    -1.01
     saltar
    -1.00
    принима
    -1.00
    🔚
    -1.00
    vedades
    -0.99
     liso
    -0.98
    POSITIVE LOGITS
    on
    1.13
    uevos
    1.12
    see
    1.08
    ba
    1.06
    ↵↵↵
    1.05
     detenidos
    1.04
    if
    1.03
    infall
    1.02
    findOneAndUpdate
    1.01
     tenuta
    1.00
    Activations Density 0.000%

    No Known Activations