© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108157
    Prev
    Next
    INDEX
    Explanations

    Independence from or political independence

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

    The neuron activates on words derived from the root “independ,” i.e. occurrences of “independence,” “independent,” or similar forms.

    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
    atalog
    -0.74
    APTER
    -0.73
    произ
    -0.72
    Ἕ
    -0.71
    ionais
    -0.70
     of
    -0.70
    酢
    -0.70
    ßten
    -0.69
    ári
    -0.69
    мей
    -0.69
    POSITIVE LOGITS
     Independence
    0.85
     day
    0.85
    Independence
    0.80
     Day
    0.79
     DAY
    0.77
     war
    0.77
     Kearns
    0.76
    咱
    0.74
     giorno
    0.73
     mercancías
    0.72
    Activations Density 0.024%

    No Known Activations