© 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. 10-GEMMASCOPE-RES-131K
    4. 68834
    Prev
    Next
    INDEX
    Explanations

    Link followed by list, span, bar, removed

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

    The neuron strongly fires on the phrase “Ocarina of Time,” i.e. mentions of that specific video-game title.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    i
    -1.43
    ;"></
    -1.34
    ☆、
    -1.21
    .'
    -1.21
    "
    -1.20
    呦
    -1.19
    Avec
    -1.15
    adeira
    -1.13
    ńst
    -1.13
    近期
    -1.11
    POSITIVE LOGITS
     solteiro
    1.65
     ilości
    1.55
     you
    1.47
     նաև
    1.43
     Zelda
    1.41
    扪
    1.40
     vorigen
    1.39
     silêncio
    1.36
     sujeito
    1.36
    ふう
    1.34
    Activations Density 0.004%

    No Known Activations