© 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. 48253
    Prev
    Next
    INDEX
    Explanations

    TM and tm abbreviations

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

    This neuron activates on occurrences of the character sequence “tm” (in any capitalization) within tokens.

    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
     remorse
    -0.81
     otherwise
    -0.74
    lichkeiten
    -0.73
    紜
    -0.71
    老
    -0.71
    大概
    -0.70
     هستیم
    -0.70
    лети
    -0.69
    移民
    -0.69
     exiles
    -0.69
    POSITIVE LOGITS
     TM
    1.18
     tm
    0.93
     TEM
    0.85
    delayed
    0.85
    hri
    0.81
    tm
    0.79
     Tem
    0.77
     Anyone
    0.77
     تم
    0.76
    balanced
    0.76
    Activations Density 0.042%

    No Known Activations