© 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. 116830
    Prev
    Next
    INDEX
    Explanations

    hypothetical past statements

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

    This neuron detects common personal pronouns (like “I,” “we,” “it,” 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
     will
    -1.37
    hibitions
    -0.87
    ibouti
    -0.87
    bunt
    -0.83
    مقال
    -0.82
    kā
    -0.81
    Couldn
    -0.81
    ئم
    -0.80
     πρέπει
    -0.79
     nebude
    -0.79
    POSITIVE LOGITS
     hätte
    2.20
     aurait
    2.17
     auraient
    1.84
     hubiera
    1.76
     hätten
    1.67
     probably
    1.54
     would
    1.45
     avrebbe
    1.33
    probably
    1.31
     olisi
    1.27
    Activations Density 0.027%

    No Known Activations