© 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. 34-GEMMASCOPE-RES-131K
    4. 90859
    Prev
    Next
    INDEX
    Explanations

    blogger profiles, code snippets

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

    The neuron fires on occurrences of the token “blogger,” such as in URLs or references to the Blogger platform.

    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
    JTable
    -0.79
    providedIn
    -0.79
    ()+"
    -0.77
     игрушки
    -0.77
     ObjectMapper
    -0.75
    '}),
    -0.75
    }{*}{}
    -0.74
    ctory
    -0.73
    》,
    -0.73
    johns
    -0.73
    POSITIVE LOGITS
     Therese
    0.82
     anstatt
    0.80
    ValueGenerated
    0.80
     bună
    0.79
    rowy
    0.79
     grátis
    0.78
    Scratch
    0.76
     instead
    0.76
     versions
    0.75
     addic
    0.75
    Activations Density 0.000%

    No Known Activations