© 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. 34-GEMMASCOPE-RES-131K
    7. 34696
    Prev
    Next
    INDEX
    Explanations

    individual and individually

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

    The neuron fires on content-bearing keywords—especially domain-specific nouns and technical terms (e.g. product names, specialized acronyms, key items).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ∓
    -0.84
    zana
    -0.75
    asi
    -0.73
    ≖
    -0.72
     }^{*}
    -0.71
    tu
    -0.71
    这类
    -0.71
    na
    -0.70
    yna
    -0.70
    gram
    -0.69
    POSITIVE LOGITS
     individual
    7.47
    individual
    6.50
    Individual
    6.19
     individually
    5.69
     Individual
    5.66
     INDIVIDUAL
    5.28
     individuales
    4.78
    individ
    4.66
     indywidual
    4.38
     индивидуаль
    4.34
    Activations Density 0.573%

    No Known Activations