© 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. 32911
    Prev
    Next
    INDEX
    Explanations

    freedom and liberation

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

    This neuron detects the apostrophe-s (“’s”) clitic, i.e. words or phrases ending in ’s (as in “it’s,” possessives, etc.).

    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
    ImageIO
    -0.86
     CONCERN
    -0.82
    ּוֹ
    -0.81
    фіка
    -0.79
     europa
    -0.79
    Mutagenicity
    -0.79
    གས་
    -0.77
     '../../../../
    -0.77
    gesch
    -0.77
     jasa
    -0.76
    POSITIVE LOGITS
     liberating
    1.45
     freeing
    1.43
     liberation
    1.38
     freedom
    1.29
     powerful
    1.16
     liberate
    1.16
    freedom
    1.10
     освобо
    1.09
     frees
    1.09
    yelitis
    1.09
    Activations Density 0.033%

    No Known Activations